Andy Dixon
d9c6ffa30f
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.
96 lines
3.8 KiB
SQL
96 lines
3.8 KiB
SQL
-- LLM providers, models, role assignments, recorded calls and versioned prompts.
|
|
|
|
CREATE TABLE llm_providers (
|
|
id uuid PRIMARY KEY,
|
|
name text NOT NULL,
|
|
kind text NOT NULL CHECK (kind IN ('openai','anthropic','ollama')),
|
|
endpoint text NOT NULL,
|
|
api_key_ref text NOT NULL DEFAULT '', -- env:, file: or enc: reference; never plaintext
|
|
allow_private boolean NOT NULL DEFAULT false,
|
|
headers jsonb NOT NULL DEFAULT '{}'::jsonb,
|
|
timeout_ms integer NOT NULL DEFAULT 60000,
|
|
enabled boolean NOT NULL DEFAULT true,
|
|
last_test_at timestamptz,
|
|
last_test_ok boolean,
|
|
last_test_msg text NOT NULL DEFAULT '',
|
|
created_at timestamptz NOT NULL DEFAULT now(),
|
|
updated_at timestamptz NOT NULL DEFAULT now()
|
|
);
|
|
CREATE UNIQUE INDEX llm_providers_name_idx ON llm_providers (lower(name));
|
|
|
|
CREATE TABLE llm_models (
|
|
id uuid PRIMARY KEY,
|
|
provider_id uuid NOT NULL REFERENCES llm_providers(id) ON DELETE CASCADE,
|
|
name text NOT NULL,
|
|
kind text NOT NULL DEFAULT 'chat' CHECK (kind IN ('chat','embedding')),
|
|
context_window integer NOT NULL DEFAULT 0,
|
|
dims integer NOT NULL DEFAULT 0,
|
|
input_cost_per_m double precision NOT NULL DEFAULT 0, -- USD per million tokens
|
|
output_cost_per_m double precision NOT NULL DEFAULT 0,
|
|
params jsonb NOT NULL DEFAULT '{}'::jsonb, -- default temperature, top_p, max_tokens
|
|
enabled boolean NOT NULL DEFAULT true,
|
|
created_at timestamptz NOT NULL DEFAULT now(),
|
|
UNIQUE (provider_id, name)
|
|
);
|
|
|
|
CREATE TABLE llm_roles (
|
|
role text PRIMARY KEY,
|
|
model_id uuid REFERENCES llm_models(id) ON DELETE SET NULL,
|
|
fallback_ids uuid[] NOT NULL DEFAULT '{}',
|
|
temperature double precision,
|
|
max_tokens integer,
|
|
updated_at timestamptz NOT NULL DEFAULT now(),
|
|
updated_by text NOT NULL DEFAULT ''
|
|
);
|
|
|
|
-- Every model call, for inspection, cost accounting and replay.
|
|
CREATE TABLE llm_calls (
|
|
id uuid PRIMARY KEY,
|
|
mind_id uuid REFERENCES minds(id),
|
|
correlation_id uuid,
|
|
role text NOT NULL,
|
|
purpose text NOT NULL DEFAULT '',
|
|
provider text NOT NULL,
|
|
model text NOT NULL,
|
|
prompt_name text NOT NULL DEFAULT '',
|
|
prompt_version integer NOT NULL DEFAULT 0,
|
|
request_hash text NOT NULL,
|
|
request jsonb NOT NULL,
|
|
response jsonb,
|
|
error text NOT NULL DEFAULT '',
|
|
prompt_tokens integer NOT NULL DEFAULT 0,
|
|
output_tokens integer NOT NULL DEFAULT 0,
|
|
cost double precision NOT NULL DEFAULT 0,
|
|
latency_ms integer NOT NULL DEFAULT 0,
|
|
seed bigint,
|
|
replayed boolean NOT NULL DEFAULT false,
|
|
created_at timestamptz NOT NULL DEFAULT now()
|
|
);
|
|
CREATE INDEX llm_calls_time_idx ON llm_calls (created_at DESC);
|
|
CREATE INDEX llm_calls_mind_idx ON llm_calls (mind_id, created_at DESC);
|
|
CREATE INDEX llm_calls_hash_idx ON llm_calls (request_hash);
|
|
CREATE INDEX llm_calls_corr_idx ON llm_calls (correlation_id) WHERE correlation_id IS NOT NULL;
|
|
|
|
CREATE TABLE prompts (
|
|
name text PRIMARY KEY,
|
|
description text NOT NULL DEFAULT '',
|
|
role text NOT NULL,
|
|
current_version integer NOT NULL DEFAULT 1,
|
|
updated_at timestamptz NOT NULL DEFAULT now()
|
|
);
|
|
|
|
CREATE TABLE prompt_versions (
|
|
id uuid PRIMARY KEY,
|
|
name text NOT NULL REFERENCES prompts(name),
|
|
version integer NOT NULL,
|
|
system text NOT NULL DEFAULT '',
|
|
template text NOT NULL,
|
|
schema jsonb,
|
|
note text NOT NULL DEFAULT '',
|
|
created_by text NOT NULL DEFAULT '',
|
|
created_at timestamptz NOT NULL DEFAULT now(),
|
|
UNIQUE (name, version)
|
|
);
|
|
CREATE TRIGGER prompt_versions_append_only BEFORE UPDATE OR DELETE ON prompt_versions
|
|
FOR EACH ROW EXECUTE FUNCTION noema_forbid_change();
|