tests/multi_turn.json

[
  {
    "id": "mt_context_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe (langue du Togo/Ghana). Tu es chaleureux et naturel."},
      {"role": "user", "content": "Nye ŋkɔ nye Kofi. Menɔ Lomé."},
      {"role": "assistant", "content": "Kofi, woezo! Lomé nye dukɔ nyui aɖe. Aleke nèle?"},
      {"role": "user", "content": "Mele nyuie. Gblɔ nuka nènya tso nye ŋu na m."}
    ],
    "eval_method": "keywords",
    "expected_keywords": ["Kofi", "Lomé"],
    "description": "Rappel du contexte — nom et ville"
  },
  {
    "id": "mt_context_02",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Mele be yeasrɔ̃ Ewe gbe. Mele anyigba si dzi la nye Canada."},
      {"role": "assistant", "content": "Eya nyo ŋutɔ! Canada tɔ eye èdi be yeàsrɔ̃ Ewe gbe. Meateŋu akpe ɖe ŋuwò. Míadze gɔme kple nya kpuiwo."},
      {"role": "user", "content": "Nyui. Afi ka menɔa ŋkɔ?"},
      {"role": "assistant", "content": "Wògblɔ be nènɔ Canada. Nèdi be yease afi la ƒe ŋkɔ a alo àdi be makae hã?"},
      {"role": "user", "content": "Ao, mele Toronto. Gake medi be nàkpe ɖe ŋunye kple salutations le Ewe me."}
    ],
    "eval_method": "composite",
    "expected_keywords": ["Toronto", "Canada"],
    "expected_format": {"contains_ewe": true, "min_length": 50},
    "description": "Suivi de contexte sur 3 tours"
  },
  {
    "id": "mt_topic_switch_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Aleke woawɔ fufu?"},
      {"role": "assistant", "content": "Fufu ƒe wɔwɔ:\n1. Tsɔ bankye alo yamɔte eye nàklé wo nyuie\n2. Da wo le tsi me\n3. To wo le tó me\n4. Tsɔ fetri alo nkrakra naa fuu kple eya"},
      {"role": "user", "content": "Nyui, akpe. Fifia medi be màbía nu tso computer programming ŋu. Aleke Pythɔn dɔwɔa?"}
    ],
    "eval_method": "composite",
    "expected_keywords": ["Python"],
    "expected_format": {"contains_ewe": true, "min_length": 80},
    "description": "Changement de sujet — adaptation"
  },
  {
    "id": "mt_correction_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Gblɔ dukɔga si le Togo la ƒe ŋkɔ nam."},
      {"role": "assistant", "content": "Togo ƒe dukɔga nye Accra."},
      {"role": "user", "content": "Ao! Eya menye ɖa o. Accra le Ghana. Togo ƒeta ŋkɔ nye ka?"}
    ],
    "eval_method": "keywords",
    "expected_keywords": ["Lomé"],
    "description": "Correction d'erreur et adaptation"
  },
  {
    "id": "mt_reference_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Medi be yeasrɔ̃ dɔ etɔ̃: Python, JavaScript, kple Rust. Dze gɔme kple gbe si bɔ ɖe asi tɔ na m."},
      {"role": "assistant", "content": "Python nye gbe si bɔ ɖe asi tɔ. Eƒe syntax sɔ kple English didi eye wòle bɔbɔe be nèasrɔ̃. Míadze gɔme kple eya."},
      {"role": "user", "content": "Eye neva evelia? Eya ka ƒe tɔtrɔ le esi ŋkɔ la dome?"}
    ],
    "eval_method": "keywords",
    "expected_keywords": ["JavaScript"],
    "description": "Référence implicite — 'le second'"
  },
  {
    "id": "mt_style_adapt_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Gblɔ nu nam abe ɖɔla aɖe ene — kpui ko, mègaɖo kuku o."},
      {"role": "assistant", "content": "Sɔ. Bía nu."},
      {"role": "user", "content": "Nuka nye AI?"},
      {"role": "assistant", "content": "Computer si ateŋu abú nu abe ame ene."},
      {"role": "user", "content": "Fifia trɔ yi ɖoɖo susɔe — gblɔ nu nam abe nufiala ene, kple kpɔɖeŋu geɖe. Gblɔ nuka nye machine learning."}
    ],
    "eval_method": "composite",
    "expected_keywords": ["machine learning"],
    "expected_format": {"contains_ewe": true, "min_length": 100},
    "description": "Adaptation de style en cours de conversation"
  },
  {
    "id": "mt_memory_long_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Nye ŋkɔ nye Esi. Mele ŋkeke 25 me. Medze programming gɔme ŋkeke 2 si va yi."},
      {"role": "assistant", "content": "Woezo Esi! Nyo be nèle ŋkeke 25 me eye nèdze programming gɔme ɣli. Ŋkeke 2 ƒe nufiamɔnu — nyui ŋutɔ! Aleke mate ŋu akpe ɖe ŋuwò egbe?"},
      {"role": "user", "content": "Medi nàkpe ɖe ŋunye be measrɔ̃ Python."},
      {"role": "assistant", "content": "Eya nyo! Python nye gbe nyui na asi-ɖoɖo. Míadze gɔme kple variables kple data types. Àsẽ be àbiá nu aɖe hã ŋgɔ?"},
      {"role": "user", "content": "Ao míadze gɔme. Gake gbã la gblɔ nam — informations ka nètsɔ ɖo nye ŋu fifia?"}
    ],
    "eval_method": "keywords",
    "expected_keywords": ["Esi", "25", "Python", "2"],
    "description": "Mémoire longue — rappel de toutes les infos"
  },
  {
    "id": "mt_task_continuation_01",
    "messages": [
      {"role": "system", "content": "Tu es Yawo, un assistant IA qui répond en Ewe."},
      {"role": "user", "content": "Kpe ɖe ŋunye be maŋlɔ email yi nye ƒe nufiala. Dze gɔme kple sujet la."},
      {"role": "assistant", "content": "Nyui! Míadze gɔme. Na sujet la gblɔ nam: Nuka ŋu nàŋlɔ nà nufiala?"},
      {"role": "user", "content": "Medi be yease ŋkeke si dɔ aɖe ƒe deadline la le ɖi yi gbe 3."},
      {"role": "assistant", "content": "Sɔ. Email ƒe sujet: 'Biabia tso deadline ƒe trɔtrɔ ŋu'\n\nFifia na body la. Aleke nèdi be nàdze gɔme?"},
      {"role": "user", "content": "Dze gɔme nam le ɖoɖo nyuitɔ (formal) me."}
    ],
    "eval_method": "composite",
    "expected_keywords": ["deadline"],
    "expected_format": {"contains_ewe": true, "min_length": 80},
    "description": "Continuation de tâche collaborative"
  }
]