feat: add provider-neutral LLM layer with secrets, budgets, recording and prompts

Phase 7 (ADR-0004). Cognitive code asks the router for a role; the
router maps roles to configured models with ordered fallbacks, applies
global and per-mind daily token budgets and a concurrency limit, records
every call (request, response, usage, latency, cost, seed, request hash)
and can serve recordings back for exact replay. Providers are raw HTTP
clients for OpenAI-compatible, Anthropic and Ollama endpoints, with
embedding support for the embed role wired into memory retrieval.

Secrets are references only: env:, file:, or enc: values encrypted with
AES-256-GCM under NOEMA_MASTER_KEY; keys are resolved at call time and
never rendered, logged or exported. Outbound HTTP refuses private and
loopback addresses at dial time unless a provider explicitly allows it,
bounds redirects and caps bodies. Provider errors are scrubbed.

Prompts are named, versioned rows with system and user templates and an
optional JSON schema; untrusted text enters only through delimited data
blocks. Six defaults are seeded and never overwritten. The UI adds the
LLM page (providers, models, role matrix, usage, errors, budgets), a
provider page with connectivity test, and a prompt manager with editor,
test runner, history, restore, clone and diff. CLI: provider, prompt.
This commit is contained in:
Andy Dixon
2026-06-23 23:43:33 +01:00
parent 0b790f34c7
commit d9c6ffa30f
43 changed files with 4138 additions and 20 deletions
+7 -1
View File
@@ -17,10 +17,13 @@ import (
"github.com/andydixon/noema/internal/brain"
"github.com/andydixon/noema/internal/config"
evstore "github.com/andydixon/noema/internal/events"
"github.com/andydixon/noema/internal/llm/prompts"
"github.com/andydixon/noema/internal/llm/router"
"github.com/andydixon/noema/internal/memory"
"github.com/andydixon/noema/internal/minds"
"github.com/andydixon/noema/internal/observability"
"github.com/andydixon/noema/internal/scheduler"
"github.com/andydixon/noema/internal/security/secrets"
"github.com/andydixon/noema/internal/storage"
"github.com/andydixon/noema/migrations"
)
@@ -31,7 +34,10 @@ func testServer(t *testing.T) (*httptest.Server, string) {
cfg := config.Defaults()
cfg.DatabaseURL = "postgres://test"
log := slog.New(slog.DiscardHandler)
deps := app.Deps{Config: cfg, Log: log, DB: pool, Auth: auth.NewService(pool, time.Hour, 2*time.Hour),
sec, _ := secrets.New("")
llmStore := router.NewStore(pool)
deps := app.Deps{Config: cfg, Log: log, DB: pool, Auth: auth.NewService(pool, time.Hour, 2*time.Hour), Secrets: sec, LLMStore: llmStore,
LLM: router.NewRouter(llmStore, sec, log, nil, 2), Prompts: prompts.NewStore(pool),
Audit: audit.New(pool, log), Metrics: observability.NewMetrics(), Minds: minds.NewStore(pool), Beliefs: beliefs.NewStore(pool), Memory: memory.NewStore(context.Background(), pool, nil), Events: evstore.NewStore(pool, evstore.NewBus(50), nil), Migrations: migrations.FS, Started: time.Now()}
ctx := context.Background()
group := scheduler.NewGroup(ctx, log)