vikingowl
3ddfd87408
Replace the Mistral + Ollama AI stack with a single Google Gemini provider backed by google.golang.org/genai. API key moves from env/Helm to the DB (AES-256-GCM, key derived from JWT_SECRET via HKDF) so it can be rotated via the admin UI without a pod restart. New: - pkg/crypto/secretbox — AES-256-GCM encrypt/decrypt for secrets at rest - pkg/ai/gemini — GeminiProvider with grounding, structured output, usage recording, and hot-reload (Reinitialize swaps client under mutex) - pkg/ai/usage — UsageRecorder interface + UsageEvent struct - domain/settings/store — DB-backed settings (model, grounding toggle, key) - domain/settings/usage — UsageRepo implementing UsageRecorder; ai_usage table - migrations 000021 (system_settings) + 000022 (ai_usage) - settings API: GET /ai, POST /ai/key, POST /ai/model, POST /ai/grounding, GET /ai/usage - admin UI: 4-card settings page — provider status, model selector, grounding toggle with quota, usage rollups + recent-calls table Removed: - pkg/ai/ollama, mistral_provider, ratelimiter (+ tests) - Helm AI_API_KEY, AI_PROVIDER, AI_MODEL_COMPLEX, AI_AGENT_DISCOVERY, AI_RATE_LIMIT_RPS env vars Call sites set Grounded+CallType: research (true/"research"), enrich Pass B (true/"enrich_b"), similarity (false/"similarity"). Integration test updated to use a stub ai.Provider instead of a fake Ollama HTTP server.
17 lines
760 B
SQL
17 lines
760 B
SQL
CREATE TABLE ai_usage (
|
|
id BIGSERIAL PRIMARY KEY,
|
|
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
|
provider TEXT NOT NULL,
|
|
model TEXT NOT NULL,
|
|
call_type TEXT NOT NULL,
|
|
input_tokens INT NOT NULL DEFAULT 0,
|
|
output_tokens INT NOT NULL DEFAULT 0,
|
|
grounded BOOLEAN NOT NULL DEFAULT false,
|
|
duration_ms INT NOT NULL DEFAULT 0,
|
|
estimated_cost_usd NUMERIC(10,6) NOT NULL DEFAULT 0,
|
|
error TEXT
|
|
);
|
|
|
|
CREATE INDEX ai_usage_created_at_desc_idx ON ai_usage (created_at DESC);
|
|
CREATE INDEX ai_usage_grounded_today_idx ON ai_usage (created_at) WHERE grounded;
|