Auditoria do meu Consumo LLM : SQLite, OpenCode, Ollama Cloud, e Por Que Minha Assinatura Profissional Está Explodindo o Mercado Mundial

@startuml
skinparam backgroundColor #FEFEFE
skinparam defaultFontSize 12

title Esquema Simplificado — OpenCode SQLite
entity "sessão" as S {
  * id : TEXT
  --
  * model : TEXT (JSON)
  * cost : REAL
  * tokens_input : INTEGER
  * tokens_output : INTEGER
  * tokens_reasoning : INTEGER
  * tokens_cache_read : INTEGER
  * tokens_cache_write : INTEGER
  * time_created : INTEGER
  * project_id : TEXT
}

entity "mensagem" as M {
  * id : TEXT
  --
  * session_id : TEXT <<FK>>
  * data : TEXT (JSON)
  * time_created : INTEGER
}

entity "projeto" as P {
  * id : TEXT
  --
  * worktree : TEXT
  * name : TEXT
}

S ||--o{ M : "session_id"
S }o--|| P : "project_id"

note right of S
A tabela session agrega
tokens + custo + modelo.
Este é nosso ponto de entrada
principal.
end note

note right of M
As mensagens individuais.
O campo dados contém
o modelo utilizado (formato JSON)
mesmo que a sessão mude de modelo no caminho.
end note

@enduml

{
  "id": "deepseek-v4-pro:cloud",
  "providerID": "ollama-cloud",
  "variant": "default"
}

const { DatabaseSync } = require('node:sqlite');
const db = new DatabaseSync(
  `${process.env.HOME}/.local/share/opencode/opencode.db`,
  { readonly: true }
);

// 1. Statistiques globales
const global = db.prepare(`
  SELECT
    COUNT(*) as sessions,
    SUM(tokens_input) as total_input,
    SUM(tokens_output) as total_output,
    SUM(tokens_reasoning) as total_reasoning,
    SUM(tokens_cache_read) as total_cache_read,
    SUM(cost) as total_cost
  FROM session
`).get();

// 2. Ventilation par modèle et fournisseur
const byModel = db.prepare(`
  SELECT
    json_extract(model, '$.id') as model_id,
    json_extract(model, '$.providerID') as provider,
    COUNT(*) as sessions,
    SUM(tokens_input) as total_input,
    SUM(tokens_output) as total_output,
    SUM(cost) as total_cost
  FROM session
  WHERE model IS NOT NULL
  GROUP BY model_id, provider
  ORDER BY SUM(tokens_input) DESC
`).all();

// 3. Par mois
const monthly = db.prepare(`
  SELECT
    strftime('%Y-%m', datetime(time_created/1000, 'unixepoch')) as month,
    COUNT(*) as sessions,
    SUM(tokens_input) as total_input,
    SUM(tokens_output) as total_output,
    SUM(cost) as total_cost
  FROM session
  WHERE time_created IS NOT NULL
  GROUP BY month
  ORDER BY month
`).all();

// 4. Messages par modèle (détection des changements intra-session)
const msgByModel = db.prepare(`
  SELECT
    json_extract(m.data, '$.model.providerID') as provider,
    json_extract(m.data, '$.model.modelID') as model_id,
    COUNT(*) as messages
  FROM message m
  WHERE json_extract(m.data, '$.model') IS NOT NULL
  GROUP BY provider, model_id
  ORDER BY COUNT(*) DESC
`).all();

console.log({ global, byModel, monthly, msgByModel });
db.close();

@startuml
skinparam backgroundColor #FEFEFE
skinparam defaultFontSize 12

title Evolução Mensual — Entrada de tokens
rectangle "Março 2026\n9 sessões\n37,7M tokens" as MARS #FFE082
rectangle "Abril 2026\n486 sessões\n1,33 Md tokens" as AVR #81C784
rectangle "Maio 2026\n527 sessões\n1,25 Md tokens" as MAI #64B5F6

MARS -right-> AVR : (No text provided for translation.)
AVR -right-> MAI : estável (período em curso)

note bottom of MAI
Maio contabilizado até o dia 18.
Projeção do mês completo: ~2,1 Md tokens
se a tendência se manter.
end note
@enduml

Modèles utilisés dans les messages (ollama-cloud provider) :
├─ deepseek-v4-pro      1 441 msgs  (32%)
├─ qwen3.5:397b         1 217 msgs  (27%)
├─ glm-5.1                712 msgs  (16%)
├─ kimi-k2.6:cloud        634 msgs  (14%)
├─ qwen3-coder:480b       414 msgs   (9%)
├─ gpt-oss:20b             34 msgs  (0,8%)
├─ qwen3-coder-next        27 msgs  (0,6%)
└─ gemma4:31b               7 msgs  (0,2%)