Compare commits

...

20 Commits

Author SHA1 Message Date
Bentlybro
5e15213846 fix(schema): rename migration dirs to 14-digit Prisma timestamps, add onUpdate: Cascade
- Rename 20260310_ → 20260310120000_ (schema) and 20260310130000_ (seed)
- Add onUpdate: Cascade to LlmModelMigration FK relations
2026-04-04 20:47:49 +00:00
Bentlybro
f0cc4ae573 Seed LLM model creators and link models
Update migration to seed LLM model creators and associate them with models. Adds INSERTs for LlmModelCreator, updates the file header comment, introduces a creator_ids CTE, and extends the LlmModel INSERT to include creatorId (joining on creator name). Existing provider seeding and model cost logic remain unchanged; ON CONFLICT behavior preserved.
2026-03-25 13:57:41 +00:00
Bently
e0282b00db Merge branch 'dev' into feat/llm-registry-schema 2026-03-23 13:43:15 +00:00
Bentlybro
9a9c36b806 Update LLM registry seeds and conflict clause
Add and rename model slugs and costs in the LLM registry seed migration (e.g. rename 'o3' -> 'o3-2025-04-16', add 'gpt-5.2-2025-12-11', Anthropic 'claude-opus-4-6'/'claude-sonnet-4-6', multiple Google Gemini and Mistralai OpenRouter entries, and other provider models). Also tighten the ON CONFLICT upsert semantics so conflicts are ignored only when "credentialId" IS NULL, preventing silent skips for credentialed entries. These changes seed new models and ensure correct conflict handling during migration.
2026-03-23 13:20:48 +00:00
Bentlybro
d5381625cd Add timestamps to LLM registry seed inserts
Update migration.sql to include createdAt and updatedAt columns/values for LlmProvider, LlmModel, and LlmModelCost seed inserts. Uses CURRENT_TIMESTAMP for both timestamp fields and adjusts the INSERT SELECT ordering for models to match the added columns. This ensures the seed data satisfies schemas that require timestamps and provides consistent created/updated metadata.
2026-03-23 12:59:30 +00:00
Bentlybro
f6ae3d6593 Update migration.sql 2026-03-23 12:43:06 +00:00
Bentlybro
0fb1b854df add llm's via migration 2026-03-23 12:37:29 +00:00
Bentlybro
64a011664a fix(schema): address Majdyz review feedback
- Add FK constraints on LlmModelMigration (sourceModelSlug, targetModelSlug → LlmModel.slug)
- Remove unused @@index([credentialProvider]) on LlmModelCost
- Remove redundant @@index([isReverted]) on LlmModelMigration (covered by composite)
- Add documentation for credentialProvider field explaining its purpose
- Add reverse relation fields to LlmModel (SourceMigrations, TargetMigrations)

Fixes data integrity: typos in migration slugs now caught at DB level.
2026-03-19 11:01:09 +00:00
Bentlybro
1db7c048d9 fix: isort import order 2026-03-19 11:01:09 +00:00
Bentlybro
4c5627c966 fix: use execute_raw_with_schema for proper multi-schema support
Per Sentry feedback: db.execute_raw ignores connection string's ?schema=
parameter and defaults to 'public' schema. This breaks in multi-schema setups.

Changes:
- Import execute_raw_with_schema from .db
- Use {schema_prefix} placeholder in query
- Call execute_raw_with_schema instead of db.execute_raw

This matches the pattern used in fix_llm_provider_credentials and other
schema-aware migrations. Works in both CI (public schema) and local
(platform schema from connection string).
2026-03-19 11:01:09 +00:00
Bentlybro
d97d137a51 fix: remove hardcoded schema prefix from migrate_llm_models query
The raw SQL query in migrate_llm_models() hardcoded platform."AgentNode"
which fails in CI where tables are in 'public' schema (not 'platform').

This code exists in dev but only runs when LLM registry has data. With our
new schema, the migration tries to run at startup and fails in CI.

Changed: UPDATE platform."AgentNode" -> UPDATE "AgentNode"

Matches pattern of all other migrations - let connection string's default
schema handle routing.
2026-03-19 11:01:09 +00:00
Bentlybro
ded9e293ff fix: remove CREATE SCHEMA to match CI environment
CI uses schema "public" as default (not "platform"), so creating
a platform schema then tables without prefix puts tables in public
but Prisma looks in platform.

Existing migrations don't create schema - they rely on connection
string's default. Remove CREATE SCHEMA IF NOT EXISTS to match.
2026-03-19 11:01:09 +00:00
Bentlybro
83d504bed2 fix: remove schema prefix from migration SQL to match existing pattern
CI failing with 'relation "platform.AgentNode" does not exist' because
Prisma generates queries differently when tables are created with
explicit schema prefixes.

Existing AutoGPT migrations use:
  CREATE TABLE "AgentNode" (...)

Not:
  CREATE TABLE "platform"."AgentNode" (...)

The connection string's ?schema=platform handles schema selection,
so explicit prefixes aren't needed and cause compatibility issues.

Changes:
- Remove all "platform". prefixes from:
  * CREATE TYPE statements
  * CREATE TABLE statements
  * CREATE INDEX statements
  * ALTER TABLE statements
  * REFERENCES clauses in foreign keys

Now matches existing migration pattern exactly.
2026-03-19 11:01:09 +00:00
Bentlybro
a5f1ffb35b fix: add partial unique indexes for data integrity
Per CodeRabbit feedback - fix 2 actual bugs:

1. Prevent multiple active migrations per source model
   - Add partial unique index: UNIQUE (sourceModelSlug) WHERE isReverted = false
   - Prevents ambiguous routing when resolving migrations

2. Allow both default and credential-specific costs
   - Remove @@unique([llmModelId, credentialProvider, unit])
   - Add 2 partial unique indexes:
     * UNIQUE (llmModelId, provider, unit) WHERE credentialId IS NULL (defaults)
     * UNIQUE (llmModelId, provider, credentialId, unit) WHERE credentialId IS NOT NULL (overrides)
   - Enables provider-level default costs + per-credential overrides

Schema comments document that these constraints exist in migration SQL.
2026-03-19 11:01:09 +00:00
Bentlybro
97c6516a14 fix: remove multiSchema - follow existing AutoGPT pattern
Remove unnecessary multiSchema configuration that broke existing models.

AutoGPT uses connection string's ?schema=platform parameter as default,
not Prisma's multiSchema feature. Existing models (User, AgentGraph, etc.)
have no @@schema() directives and work fine.

Changes:
- Remove schemas = ["platform", "public"] from datasource
- Remove "multiSchema" from previewFeatures
- Remove all @@schema() directives from LLM models and enum

Migration SQL already creates tables in platform schema explicitly
(CREATE TABLE "platform"."LlmProvider" etc.) which is correct.

This matches the existing pattern used throughout the codebase.
2026-03-19 11:01:09 +00:00
Bentlybro
876dde8bc7 fix: address CodeRabbit design feedback
Per CodeRabbit review:

1. **Safety: Change capability defaults false → safer for partial seeding**
   - supportsTools: true → false
   - supportsJsonOutput: true → false
   - Prevents partially-seeded rows from being assumed capable

2. **Clarity: Rename supportsParallelTool → supportsParallelToolCalls**
   - More explicit about what the field represents

3. **Performance: Remove redundant indexes**
   - Drop @@index([llmModelId]) - covered by unique constraint
   - Drop @@index([sourceModelSlug]) - covered by composite index
   - Reduces write overhead and storage

4. **Documentation: Acknowledge customCreditCost limitation**
   - It's unit-agnostic (doesn't distinguish RUN vs TOKENS)
   - Noted as TODO for follow-up PR with proper unit-aware override

Schema + migration both updated to match.
2026-03-19 11:01:09 +00:00
Bentlybro
0bfdd74b25 fix: add @@schema("platform") to LlmCostUnit enum
Sentry caught this - enums also need @@schema directive with multiSchema enabled.
Without it, Prisma looks for enum in public schema but it's created in platform.
2026-03-19 11:01:09 +00:00
Bentlybro
a7d2f81b18 feat: add database CHECK constraints for data integrity
Per CodeRabbit feedback - enforce numeric domain rules at DB level:

Migration:
- priceTier: CHECK (priceTier BETWEEN 1 AND 3)
- creditCost: CHECK (creditCost >= 0)
- nodeCount: CHECK (nodeCount >= 0)
- customCreditCost: CHECK (customCreditCost IS NULL OR customCreditCost >= 0)

Schema comments:
- Document constraints inline for developer visibility

Prevents invalid data (negative costs, out-of-range tiers) from
entering the database, matching backend/blocks/llm.py contract.
2026-03-19 11:01:09 +00:00
Bentlybro
3699eaa556 fix: use @@schema() instead of @@map() for platform schema + create schema in migration
Critical fixes from PR review:

1. Replace @@map("platform.ModelName") with @@schema("platform")
   - Sentry correctly identified: Prisma was looking for literal table "platform.LlmProvider" with dot
   - Proper syntax: enable multiSchema feature + use @@schema directive

2. Create platform schema in migration
   - CI failed: schema "platform" does not exist
   - Add CREATE SCHEMA IF NOT EXISTS at start of migration

Schema changes:
- datasource: add schemas = ["platform", "public"]
- generator: add "multiSchema" to previewFeatures
- All 5 models: @@map() → @@schema("platform")

Migration changes:
- Add CREATE SCHEMA IF NOT EXISTS "platform" before enum creation

Fixes CI failure and Sentry-identified bug.
2026-03-19 11:01:09 +00:00
Bentlybro
21adf9e0fb feat(platform): Add LLM registry database schema
Add Prisma schema and migration for dynamic LLM model registry:

Schema additions:
- LlmProvider: Registry of LLM providers (OpenAI, Anthropic, etc.)
- LlmModel: Individual models with capabilities and metadata
- LlmModelCost: Per-model pricing configuration
- LlmModelCreator: Model creators/trainers (OpenAI, Meta, etc.)
- LlmModelMigration: Track model migrations and reverts
- LlmCostUnit enum: RUN vs TOKENS pricing units

Key features:
- Model-specific capabilities (tools, JSON, reasoning, parallel calls)
- Flexible creator/provider separation (e.g., Meta model via Hugging Face)
- Migration tracking with custom pricing overrides
- Indexes for performance on common queries

Part 1 of incremental LLM registry implementation.
Refs: Draft PR #11699
2026-03-19 11:01:08 +00:00
4 changed files with 600 additions and 4 deletions

View File

@@ -36,7 +36,7 @@ from backend.util.models import Pagination
from backend.util.request import parse_url from backend.util.request import parse_url
from .block import BlockInput from .block import BlockInput
from .db import BaseDbModel from .db import BaseDbModel, execute_raw_with_schema
from .db import prisma as db from .db import prisma as db
from .db import query_raw_with_schema, transaction from .db import query_raw_with_schema, transaction
from .dynamic_fields import is_tool_pin, sanitize_pin_name from .dynamic_fields import is_tool_pin, sanitize_pin_name
@@ -1670,15 +1670,15 @@ async def migrate_llm_models(migrate_to: LlmModel):
# Update each block # Update each block
for id, path in llm_model_fields.items(): for id, path in llm_model_fields.items():
query = f""" query = f"""
UPDATE platform."AgentNode" UPDATE {{schema_prefix}}"AgentNode"
SET "constantInput" = jsonb_set("constantInput", $1, to_jsonb($2), true) SET "constantInput" = jsonb_set("constantInput", $1, to_jsonb($2), true)
WHERE "agentBlockId" = $3 WHERE "agentBlockId" = $3
AND "constantInput" ? ($4)::text AND "constantInput" ? ($4)::text
AND "constantInput"->>($4)::text NOT IN {escaped_enum_values} AND "constantInput"->>($4)::text NOT IN {escaped_enum_values}
""" """
await db.execute_raw( await execute_raw_with_schema(
query, # type: ignore - is supposed to be LiteralString query,
[path], [path],
migrate_to.value, migrate_to.value,
id, id,

View File

@@ -0,0 +1,148 @@
-- CreateEnum
CREATE TYPE "LlmCostUnit" AS ENUM ('RUN', 'TOKENS');
-- CreateTable
CREATE TABLE "LlmProvider" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"name" TEXT NOT NULL,
"displayName" TEXT NOT NULL,
"description" TEXT,
"defaultCredentialProvider" TEXT,
"defaultCredentialId" TEXT,
"defaultCredentialType" TEXT,
"metadata" JSONB NOT NULL DEFAULT '{}',
CONSTRAINT "LlmProvider_pkey" PRIMARY KEY ("id")
);
-- CreateTable
CREATE TABLE "LlmModelCreator" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"name" TEXT NOT NULL,
"displayName" TEXT NOT NULL,
"description" TEXT,
"websiteUrl" TEXT,
"logoUrl" TEXT,
"metadata" JSONB NOT NULL DEFAULT '{}',
CONSTRAINT "LlmModelCreator_pkey" PRIMARY KEY ("id")
);
-- CreateTable
CREATE TABLE "LlmModel" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"slug" TEXT NOT NULL,
"displayName" TEXT NOT NULL,
"description" TEXT,
"providerId" TEXT NOT NULL,
"creatorId" TEXT,
"contextWindow" INTEGER NOT NULL,
"maxOutputTokens" INTEGER,
"priceTier" INTEGER NOT NULL DEFAULT 1,
"isEnabled" BOOLEAN NOT NULL DEFAULT true,
"isRecommended" BOOLEAN NOT NULL DEFAULT false,
"supportsTools" BOOLEAN NOT NULL DEFAULT false,
"supportsJsonOutput" BOOLEAN NOT NULL DEFAULT false,
"supportsReasoning" BOOLEAN NOT NULL DEFAULT false,
"supportsParallelToolCalls" BOOLEAN NOT NULL DEFAULT false,
"capabilities" JSONB NOT NULL DEFAULT '{}',
"metadata" JSONB NOT NULL DEFAULT '{}',
CONSTRAINT "LlmModel_pkey" PRIMARY KEY ("id")
);
-- CreateTable
CREATE TABLE "LlmModelCost" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"unit" "LlmCostUnit" NOT NULL DEFAULT 'RUN',
"creditCost" INTEGER NOT NULL,
"credentialProvider" TEXT NOT NULL,
"credentialId" TEXT,
"credentialType" TEXT,
"currency" TEXT,
"metadata" JSONB NOT NULL DEFAULT '{}',
"llmModelId" TEXT NOT NULL,
CONSTRAINT "LlmModelCost_pkey" PRIMARY KEY ("id")
);
-- CreateTable
CREATE TABLE "LlmModelMigration" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"sourceModelSlug" TEXT NOT NULL,
"targetModelSlug" TEXT NOT NULL,
"reason" TEXT,
"migratedNodeIds" JSONB NOT NULL DEFAULT '[]',
"nodeCount" INTEGER NOT NULL,
"customCreditCost" INTEGER,
"isReverted" BOOLEAN NOT NULL DEFAULT false,
"revertedAt" TIMESTAMP(3),
CONSTRAINT "LlmModelMigration_pkey" PRIMARY KEY ("id")
);
-- CreateIndex
CREATE UNIQUE INDEX "LlmProvider_name_key" ON "LlmProvider"("name");
-- CreateIndex
CREATE UNIQUE INDEX "LlmModelCreator_name_key" ON "LlmModelCreator"("name");
-- CreateIndex
CREATE UNIQUE INDEX "LlmModel_slug_key" ON "LlmModel"("slug");
-- CreateIndex
CREATE INDEX "LlmModel_providerId_isEnabled_idx" ON "LlmModel"("providerId", "isEnabled");
-- CreateIndex
CREATE INDEX "LlmModel_creatorId_idx" ON "LlmModel"("creatorId");
-- CreateIndex (partial unique for default costs - no specific credential)
CREATE UNIQUE INDEX "LlmModelCost_default_cost_key" ON "LlmModelCost"("llmModelId", "credentialProvider", "unit") WHERE "credentialId" IS NULL;
-- CreateIndex (partial unique for credential-specific costs)
CREATE UNIQUE INDEX "LlmModelCost_credential_cost_key" ON "LlmModelCost"("llmModelId", "credentialProvider", "credentialId", "unit") WHERE "credentialId" IS NOT NULL;
-- CreateIndex
CREATE INDEX "LlmModelMigration_targetModelSlug_idx" ON "LlmModelMigration"("targetModelSlug");
-- CreateIndex
CREATE INDEX "LlmModelMigration_sourceModelSlug_isReverted_idx" ON "LlmModelMigration"("sourceModelSlug", "isReverted");
-- CreateIndex (partial unique to prevent multiple active migrations per source)
CREATE UNIQUE INDEX "LlmModelMigration_active_source_key" ON "LlmModelMigration"("sourceModelSlug") WHERE "isReverted" = false;
-- AddForeignKey
ALTER TABLE "LlmModel" ADD CONSTRAINT "LlmModel_providerId_fkey" FOREIGN KEY ("providerId") REFERENCES "LlmProvider"("id") ON DELETE RESTRICT ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "LlmModel" ADD CONSTRAINT "LlmModel_creatorId_fkey" FOREIGN KEY ("creatorId") REFERENCES "LlmModelCreator"("id") ON DELETE SET NULL ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "LlmModelCost" ADD CONSTRAINT "LlmModelCost_llmModelId_fkey" FOREIGN KEY ("llmModelId") REFERENCES "LlmModel"("id") ON DELETE CASCADE ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "LlmModelMigration" ADD CONSTRAINT "LlmModelMigration_sourceModelSlug_fkey" FOREIGN KEY ("sourceModelSlug") REFERENCES "LlmModel"("slug") ON DELETE RESTRICT ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "LlmModelMigration" ADD CONSTRAINT "LlmModelMigration_targetModelSlug_fkey" FOREIGN KEY ("targetModelSlug") REFERENCES "LlmModel"("slug") ON DELETE RESTRICT ON UPDATE CASCADE;
-- AddCheckConstraints (enforce data integrity)
ALTER TABLE "LlmModel"
ADD CONSTRAINT "LlmModel_priceTier_check" CHECK ("priceTier" BETWEEN 1 AND 3);
ALTER TABLE "LlmModelCost"
ADD CONSTRAINT "LlmModelCost_creditCost_check" CHECK ("creditCost" >= 0);
ALTER TABLE "LlmModelMigration"
ADD CONSTRAINT "LlmModelMigration_nodeCount_check" CHECK ("nodeCount" >= 0),
ADD CONSTRAINT "LlmModelMigration_customCreditCost_check" CHECK ("customCreditCost" IS NULL OR "customCreditCost" >= 0);

View File

@@ -0,0 +1,287 @@
-- Seed LLM Registry from existing hard-coded data
-- This migration populates the LlmProvider, LlmModelCreator, LlmModel, and LlmModelCost tables
-- with data from the existing MODEL_METADATA and MODEL_COST dictionaries
-- Insert Providers
INSERT INTO "LlmProvider" ("id", "createdAt", "updatedAt", "name", "displayName", "description", "defaultCredentialProvider", "defaultCredentialType", "metadata")
VALUES
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'openai', 'OpenAI', 'OpenAI language models', 'openai', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'anthropic', 'Anthropic', 'Anthropic Claude models', 'anthropic', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'groq', 'Groq', 'Groq inference API', 'groq', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'open_router', 'OpenRouter', 'OpenRouter unified API', 'open_router', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'aiml_api', 'AI/ML API', 'AI/ML API models', 'aiml_api', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'ollama', 'Ollama', 'Ollama local models', 'ollama', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'llama_api', 'Llama API', 'Llama API models', 'llama_api', 'api_key', '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'v0', 'v0', 'v0 by Vercel models', 'v0', 'api_key', '{}'::jsonb)
ON CONFLICT ("name") DO NOTHING;
-- Insert Model Creators
INSERT INTO "LlmModelCreator" ("id", "createdAt", "updatedAt", "name", "displayName", "description", "websiteUrl", "logoUrl", "metadata")
VALUES
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'openai', 'OpenAI', 'Creator of GPT, O1, O3, and DALL-E models', 'https://openai.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'anthropic', 'Anthropic', 'Creator of Claude AI models', 'https://anthropic.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'meta', 'Meta', 'Creator of Llama foundation models', 'https://llama.meta.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'google', 'Google', 'Creator of Gemini and PaLM models', 'https://deepmind.google', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'mistralai', 'Mistral AI', 'Creator of Mistral and Codestral models', 'https://mistral.ai', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'cohere', 'Cohere', 'Creator of Command language models', 'https://cohere.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'deepseek', 'DeepSeek', 'Creator of DeepSeek reasoning models', 'https://deepseek.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'alibaba', 'Alibaba', 'Creator of Qwen language models', 'https://qwenlm.github.io', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'nvidia', 'NVIDIA', 'Creator of Nemotron models', 'https://nvidia.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'vercel', 'Vercel', 'Creator of v0 AI models', 'https://v0.dev', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'microsoft', 'Microsoft', 'Creator of Phi models', 'https://microsoft.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'xai', 'xAI', 'Creator of Grok models', 'https://x.ai', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'perplexity', 'Perplexity AI', 'Creator of Sonar search models', 'https://perplexity.ai', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'nousresearch', 'Nous Research', 'Creator of Hermes language models', 'https://nousresearch.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'amazon', 'Amazon', 'Creator of Nova language models', 'https://aws.amazon.com', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'gryphe', 'Gryphe', 'Creator of MythoMax models', 'https://huggingface.co/Gryphe', NULL, '{}'::jsonb),
(gen_random_uuid(), CURRENT_TIMESTAMP, CURRENT_TIMESTAMP, 'moonshotai', 'Moonshot AI', 'Creator of Kimi language models', 'https://moonshot.ai', NULL, '{}'::jsonb)
ON CONFLICT ("name") DO NOTHING;
-- Insert Models (using CTEs to reference provider and creator IDs)
WITH provider_ids AS (
SELECT "id", "name" FROM "LlmProvider"
),
creator_ids AS (
SELECT "id", "name" FROM "LlmModelCreator"
)
INSERT INTO "LlmModel" ("id", "createdAt", "updatedAt", "slug", "displayName", "description", "providerId", "creatorId", "contextWindow", "maxOutputTokens", "isEnabled", "capabilities", "metadata")
SELECT
gen_random_uuid(),
CURRENT_TIMESTAMP,
CURRENT_TIMESTAMP,
model_slug,
model_display_name,
NULL,
p."id",
c."id",
context_window,
max_output_tokens,
true,
'{}'::jsonb,
'{}'::jsonb
FROM (VALUES
-- OpenAI models (creator: openai)
('o3-2025-04-16', 'O3', 'openai', 'openai', 200000, 100000),
('o3-mini', 'O3 Mini', 'openai', 'openai', 200000, 100000),
('o1', 'O1', 'openai', 'openai', 200000, 100000),
('o1-mini', 'O1 Mini', 'openai', 'openai', 128000, 65536),
('gpt-5.2-2025-12-11', 'GPT-5.2', 'openai', 'openai', 400000, 128000),
('gpt-5-2025-08-07', 'GPT 5', 'openai', 'openai', 400000, 128000),
('gpt-5.1-2025-11-13', 'GPT 5.1', 'openai', 'openai', 400000, 128000),
('gpt-5-mini-2025-08-07', 'GPT 5 Mini', 'openai', 'openai', 400000, 128000),
('gpt-5-nano-2025-08-07', 'GPT 5 Nano', 'openai', 'openai', 400000, 128000),
('gpt-5-chat-latest', 'GPT 5 Chat', 'openai', 'openai', 400000, 16384),
('gpt-4.1-2025-04-14', 'GPT 4.1', 'openai', 'openai', 1000000, 32768),
('gpt-4.1-mini-2025-04-14', 'GPT 4.1 Mini', 'openai', 'openai', 1047576, 32768),
('gpt-4o-mini', 'GPT 4o Mini', 'openai', 'openai', 128000, 16384),
('gpt-4o', 'GPT 4o', 'openai', 'openai', 128000, 16384),
('gpt-4-turbo', 'GPT 4 Turbo', 'openai', 'openai', 128000, 4096),
-- Anthropic models (creator: anthropic)
('claude-opus-4-6', 'Claude Opus 4.6', 'anthropic', 'anthropic', 200000, 128000),
('claude-sonnet-4-6', 'Claude Sonnet 4.6', 'anthropic', 'anthropic', 200000, 64000),
('claude-opus-4-1-20250805', 'Claude 4.1 Opus', 'anthropic', 'anthropic', 200000, 32000),
('claude-opus-4-20250514', 'Claude 4 Opus', 'anthropic', 'anthropic', 200000, 32000),
('claude-sonnet-4-20250514', 'Claude 4 Sonnet', 'anthropic', 'anthropic', 200000, 64000),
('claude-opus-4-5-20251101', 'Claude 4.5 Opus', 'anthropic', 'anthropic', 200000, 64000),
('claude-sonnet-4-5-20250929', 'Claude 4.5 Sonnet', 'anthropic', 'anthropic', 200000, 64000),
('claude-haiku-4-5-20251001', 'Claude 4.5 Haiku', 'anthropic', 'anthropic', 200000, 64000),
('claude-3-haiku-20240307', 'Claude 3 Haiku', 'anthropic', 'anthropic', 200000, 4096),
-- AI/ML API models (creators: alibaba, nvidia, meta)
('Qwen/Qwen2.5-72B-Instruct-Turbo', 'Qwen 2.5 72B', 'aiml_api', 'alibaba', 32000, 8000),
('nvidia/llama-3.1-nemotron-70b-instruct', 'Llama 3.1 Nemotron 70B', 'aiml_api', 'nvidia', 128000, 40000),
('meta-llama/Llama-3.3-70B-Instruct-Turbo', 'Llama 3.3 70B', 'aiml_api', 'meta', 128000, NULL),
('meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', 'Meta Llama 3.1 70B', 'aiml_api', 'meta', 131000, 2000),
('meta-llama/Llama-3.2-3B-Instruct-Turbo', 'Llama 3.2 3B', 'aiml_api', 'meta', 128000, NULL),
-- Groq models (creator: meta for Llama)
('llama-3.3-70b-versatile', 'Llama 3.3 70B', 'groq', 'meta', 128000, 32768),
('llama-3.1-8b-instant', 'Llama 3.1 8B', 'groq', 'meta', 128000, 8192),
-- Ollama models (creators: meta for Llama, mistralai for Mistral)
('llama3.3', 'Llama 3.3', 'ollama', 'meta', 8192, NULL),
('llama3.2', 'Llama 3.2', 'ollama', 'meta', 8192, NULL),
('llama3', 'Llama 3', 'ollama', 'meta', 8192, NULL),
('llama3.1:405b', 'Llama 3.1 405B', 'ollama', 'meta', 8192, NULL),
('dolphin-mistral:latest', 'Dolphin Mistral', 'ollama', 'mistralai', 32768, NULL),
-- OpenRouter models (creators: google, mistralai, cohere, deepseek, perplexity, nousresearch, openai, amazon, microsoft, gryphe, meta, xai, moonshotai, alibaba)
('google/gemini-2.5-pro-preview-03-25', 'Gemini 2.5 Pro', 'open_router', 'google', 1050000, 8192),
('google/gemini-2.5-pro', 'Gemini 2.5 Pro', 'open_router', 'google', 1048576, 65536),
('google/gemini-3.1-pro-preview', 'Gemini 3.1 Pro Preview', 'open_router', 'google', 1048576, 65536),
('google/gemini-3-flash-preview', 'Gemini 3 Flash Preview', 'open_router', 'google', 1048576, 65536),
('google/gemini-2.5-flash', 'Gemini 2.5 Flash', 'open_router', 'google', 1048576, 65535),
('google/gemini-2.0-flash-001', 'Gemini 2.0 Flash', 'open_router', 'google', 1048576, 8192),
('google/gemini-3.1-flash-lite-preview', 'Gemini 3.1 Flash Lite Preview', 'open_router', 'google', 1048576, 65536),
('google/gemini-2.5-flash-lite-preview-06-17', 'Gemini 2.5 Flash Lite Preview', 'open_router', 'google', 1048576, 65535),
('google/gemini-2.0-flash-lite-001', 'Gemini 2.0 Flash Lite', 'open_router', 'google', 1048576, 8192),
('mistralai/mistral-nemo', 'Mistral Nemo', 'open_router', 'mistralai', 128000, 4096),
('mistralai/mistral-large-2512', 'Mistral Large 3 2512', 'open_router', 'mistralai', 262144, NULL),
('mistralai/mistral-medium-3.1', 'Mistral Medium 3.1', 'open_router', 'mistralai', 131072, NULL),
('mistralai/mistral-small-3.2-24b-instruct', 'Mistral Small 3.2 24B', 'open_router', 'mistralai', 131072, 131072),
('mistralai/codestral-2508', 'Codestral 2508', 'open_router', 'mistralai', 256000, NULL),
('cohere/command-r-08-2024', 'Command R', 'open_router', 'cohere', 128000, 4096),
('cohere/command-r-plus-08-2024', 'Command R Plus', 'open_router', 'cohere', 128000, 4096),
('cohere/command-a-03-2025', 'Command A 03.2025', 'open_router', 'cohere', 256000, 8192),
('cohere/command-a-reasoning-08-2025', 'Command A Reasoning 08.2025', 'open_router', 'cohere', 256000, 32768),
('cohere/command-a-translate-08-2025', 'Command A Translate 08.2025', 'open_router', 'cohere', 128000, 8192),
('cohere/command-a-vision-07-2025', 'Command A Vision 07.2025', 'open_router', 'cohere', 128000, 8192),
('deepseek/deepseek-chat', 'DeepSeek Chat', 'open_router', 'deepseek', 64000, 2048),
('deepseek/deepseek-r1-0528', 'DeepSeek R1', 'open_router', 'deepseek', 163840, 163840),
('perplexity/sonar', 'Perplexity Sonar', 'open_router', 'perplexity', 127000, 8000),
('perplexity/sonar-pro', 'Perplexity Sonar Pro', 'open_router', 'perplexity', 200000, 8000),
('perplexity/sonar-deep-research', 'Perplexity Sonar Deep Research', 'open_router', 'perplexity', 128000, 16000),
('perplexity/sonar-reasoning-pro', 'Sonar Reasoning Pro', 'open_router', 'perplexity', 128000, 8000),
('nousresearch/hermes-3-llama-3.1-405b', 'Hermes 3 Llama 3.1 405B', 'open_router', 'nousresearch', 131000, 4096),
('nousresearch/hermes-3-llama-3.1-70b', 'Hermes 3 Llama 3.1 70B', 'open_router', 'nousresearch', 12288, 12288),
('openai/gpt-oss-120b', 'GPT OSS 120B', 'open_router', 'openai', 131072, 131072),
('openai/gpt-oss-20b', 'GPT OSS 20B', 'open_router', 'openai', 131072, 32768),
('amazon/nova-lite-v1', 'Amazon Nova Lite', 'open_router', 'amazon', 300000, 5120),
('amazon/nova-micro-v1', 'Amazon Nova Micro', 'open_router', 'amazon', 128000, 5120),
('amazon/nova-pro-v1', 'Amazon Nova Pro', 'open_router', 'amazon', 300000, 5120),
('microsoft/wizardlm-2-8x22b', 'WizardLM 2 8x22B', 'open_router', 'microsoft', 65536, 4096),
('microsoft/phi-4', 'Phi-4', 'open_router', 'microsoft', 16384, 16384),
('gryphe/mythomax-l2-13b', 'MythoMax L2 13B', 'open_router', 'gryphe', 4096, 4096),
('meta-llama/llama-4-scout', 'Llama 4 Scout', 'open_router', 'meta', 131072, 131072),
('meta-llama/llama-4-maverick', 'Llama 4 Maverick', 'open_router', 'meta', 1048576, 1000000),
('x-ai/grok-3', 'Grok 3', 'open_router', 'xai', 131072, 131072),
('x-ai/grok-4', 'Grok 4', 'open_router', 'xai', 256000, 256000),
('x-ai/grok-4-fast', 'Grok 4 Fast', 'open_router', 'xai', 2000000, 30000),
('x-ai/grok-4.1-fast', 'Grok 4.1 Fast', 'open_router', 'xai', 2000000, 30000),
('x-ai/grok-code-fast-1', 'Grok Code Fast 1', 'open_router', 'xai', 256000, 10000),
('moonshotai/kimi-k2', 'Kimi K2', 'open_router', 'moonshotai', 131000, 131000),
('qwen/qwen3-235b-a22b-thinking-2507', 'Qwen 3 235B Thinking', 'open_router', 'alibaba', 262144, 262144),
('qwen/qwen3-coder', 'Qwen 3 Coder', 'open_router', 'alibaba', 262144, 262144),
-- Llama API models (creator: meta)
('Llama-4-Scout-17B-16E-Instruct-FP8', 'Llama 4 Scout', 'llama_api', 'meta', 128000, 4028),
('Llama-4-Maverick-17B-128E-Instruct-FP8', 'Llama 4 Maverick', 'llama_api', 'meta', 128000, 4028),
('Llama-3.3-8B-Instruct', 'Llama 3.3 8B', 'llama_api', 'meta', 128000, 4028),
('Llama-3.3-70B-Instruct', 'Llama 3.3 70B', 'llama_api', 'meta', 128000, 4028),
-- v0 models (creator: vercel)
('v0-1.5-md', 'v0 1.5 MD', 'v0', 'vercel', 128000, 64000),
('v0-1.5-lg', 'v0 1.5 LG', 'v0', 'vercel', 512000, 64000),
('v0-1.0-md', 'v0 1.0 MD', 'v0', 'vercel', 128000, 64000)
) AS models(model_slug, model_display_name, provider_name, creator_name, context_window, max_output_tokens)
JOIN provider_ids p ON p."name" = models.provider_name
JOIN creator_ids c ON c."name" = models.creator_name
ON CONFLICT ("slug") DO NOTHING;
-- Insert Costs (using CTEs to reference model IDs)
WITH model_ids AS (
SELECT "id", "slug", "providerId" FROM "LlmModel"
),
provider_ids AS (
SELECT "id", "name" FROM "LlmProvider"
)
INSERT INTO "LlmModelCost" ("id", "createdAt", "updatedAt", "unit", "creditCost", "credentialProvider", "credentialId", "credentialType", "currency", "metadata", "llmModelId")
SELECT
gen_random_uuid(),
CURRENT_TIMESTAMP,
CURRENT_TIMESTAMP,
'RUN'::"LlmCostUnit",
cost,
p."name",
NULL,
'api_key',
NULL,
'{}'::jsonb,
m."id"
FROM (VALUES
-- OpenAI costs
('o3-2025-04-16', 4),
('o3-mini', 2),
('o1', 16),
('o1-mini', 4),
('gpt-5.2-2025-12-11', 5),
('gpt-5-2025-08-07', 2),
('gpt-5.1-2025-11-13', 5),
('gpt-5-mini-2025-08-07', 1),
('gpt-5-nano-2025-08-07', 1),
('gpt-5-chat-latest', 5),
('gpt-4.1-2025-04-14', 2),
('gpt-4.1-mini-2025-04-14', 1),
('gpt-4o-mini', 1),
('gpt-4o', 3),
('gpt-4-turbo', 10),
-- Anthropic costs
('claude-opus-4-6', 21),
('claude-sonnet-4-6', 5),
('claude-opus-4-1-20250805', 21),
('claude-opus-4-20250514', 21),
('claude-sonnet-4-20250514', 5),
('claude-haiku-4-5-20251001', 4),
('claude-opus-4-5-20251101', 14),
('claude-sonnet-4-5-20250929', 9),
('claude-3-haiku-20240307', 1),
-- AI/ML API costs
('Qwen/Qwen2.5-72B-Instruct-Turbo', 1),
('nvidia/llama-3.1-nemotron-70b-instruct', 1),
('meta-llama/Llama-3.3-70B-Instruct-Turbo', 1),
('meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', 1),
('meta-llama/Llama-3.2-3B-Instruct-Turbo', 1),
-- Groq costs
('llama-3.3-70b-versatile', 1),
('llama-3.1-8b-instant', 1),
-- Ollama costs
('llama3.3', 1),
('llama3.2', 1),
('llama3', 1),
('llama3.1:405b', 1),
('dolphin-mistral:latest', 1),
-- OpenRouter costs
('google/gemini-2.5-pro-preview-03-25', 4),
('google/gemini-2.5-pro', 4),
('google/gemini-3.1-pro-preview', 5),
('google/gemini-3-flash-preview', 3),
('google/gemini-3.1-flash-lite-preview', 1),
('mistralai/mistral-nemo', 1),
('mistralai/mistral-large-2512', 3),
('mistralai/mistral-medium-3.1', 2),
('mistralai/mistral-small-3.2-24b-instruct', 1),
('mistralai/codestral-2508', 2),
('cohere/command-r-08-2024', 1),
('cohere/command-r-plus-08-2024', 3),
('cohere/command-a-03-2025', 2),
('cohere/command-a-reasoning-08-2025', 3),
('cohere/command-a-translate-08-2025', 1),
('cohere/command-a-vision-07-2025', 2),
('deepseek/deepseek-chat', 2),
('perplexity/sonar', 1),
('perplexity/sonar-pro', 5),
('perplexity/sonar-deep-research', 10),
('perplexity/sonar-reasoning-pro', 5),
('nousresearch/hermes-3-llama-3.1-405b', 1),
('nousresearch/hermes-3-llama-3.1-70b', 1),
('amazon/nova-lite-v1', 1),
('amazon/nova-micro-v1', 1),
('amazon/nova-pro-v1', 1),
('microsoft/wizardlm-2-8x22b', 1),
('microsoft/phi-4', 1),
('gryphe/mythomax-l2-13b', 1),
('meta-llama/llama-4-scout', 1),
('meta-llama/llama-4-maverick', 1),
('x-ai/grok-3', 5),
('x-ai/grok-4', 9),
('x-ai/grok-4-fast', 1),
('x-ai/grok-4.1-fast', 1),
('x-ai/grok-code-fast-1', 1),
('moonshotai/kimi-k2', 1),
('qwen/qwen3-235b-a22b-thinking-2507', 1),
('qwen/qwen3-coder', 9),
('google/gemini-2.5-flash', 1),
('google/gemini-2.0-flash-001', 1),
('google/gemini-2.5-flash-lite-preview-06-17', 1),
('google/gemini-2.0-flash-lite-001', 1),
('deepseek/deepseek-r1-0528', 1),
('openai/gpt-oss-120b', 1),
('openai/gpt-oss-20b', 1),
-- Llama API costs
('Llama-4-Scout-17B-16E-Instruct-FP8', 1),
('Llama-4-Maverick-17B-128E-Instruct-FP8', 1),
('Llama-3.3-8B-Instruct', 1),
('Llama-3.3-70B-Instruct', 1),
-- v0 costs
('v0-1.5-md', 1),
('v0-1.5-lg', 2),
('v0-1.0-md', 1)
) AS costs(model_slug, cost)
JOIN model_ids m ON m."slug" = costs.model_slug
JOIN provider_ids p ON p."id" = m."providerId"
ON CONFLICT ("llmModelId", "credentialProvider", "unit") WHERE "credentialId" IS NULL DO NOTHING;

View File

@@ -1301,3 +1301,164 @@ model OAuthRefreshToken {
@@index([userId, applicationId]) @@index([userId, applicationId])
@@index([expiresAt]) // For cleanup @@index([expiresAt]) // For cleanup
} }
// ============================================================================
// LLM Registry Models
// ============================================================================
enum LlmCostUnit {
RUN
TOKENS
}
model LlmProvider {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
name String @unique
displayName String
description String?
defaultCredentialProvider String?
defaultCredentialId String?
defaultCredentialType String?
metadata Json @default("{}")
Models LlmModel[]
}
model LlmModel {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
slug String @unique
displayName String
description String?
providerId String
Provider LlmProvider @relation(fields: [providerId], references: [id], onDelete: Restrict)
// Creator is the organization that created/trained the model (e.g., OpenAI, Meta)
// This is distinct from the provider who hosts/serves the model (e.g., OpenRouter)
creatorId String?
Creator LlmModelCreator? @relation(fields: [creatorId], references: [id], onDelete: SetNull)
contextWindow Int
maxOutputTokens Int?
priceTier Int @default(1) // 1=cheapest, 2=medium, 3=expensive (DB constraint: 1-3)
isEnabled Boolean @default(true)
isRecommended Boolean @default(false)
// Model-specific capabilities
// These vary per model even within the same provider (e.g., Hugging Face)
// Default to false for safety - partially-seeded rows should not be assumed capable
supportsTools Boolean @default(false)
supportsJsonOutput Boolean @default(false)
supportsReasoning Boolean @default(false)
supportsParallelToolCalls Boolean @default(false)
capabilities Json @default("{}")
metadata Json @default("{}")
Costs LlmModelCost[]
SourceMigrations LlmModelMigration[] @relation("SourceMigrations")
TargetMigrations LlmModelMigration[] @relation("TargetMigrations")
@@index([providerId, isEnabled])
@@index([creatorId])
// Note: slug already has @unique which creates an implicit index
}
model LlmModelCost {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
unit LlmCostUnit @default(RUN)
creditCost Int // DB constraint: >= 0
// Provider identifier (e.g., "openai", "anthropic", "openrouter")
// Used to determine which credential system provides the API key.
// Allows different pricing for:
// - Default provider costs (WHERE credentialId IS NULL)
// - User's own API key costs (WHERE credentialId IS NOT NULL)
credentialProvider String
credentialId String?
credentialType String?
currency String?
metadata Json @default("{}")
llmModelId String
Model LlmModel @relation(fields: [llmModelId], references: [id], onDelete: Cascade)
// Note: Unique constraints are implemented as partial indexes in migration SQL:
// - One for default costs (WHERE credentialId IS NULL)
// - One for credential-specific costs (WHERE credentialId IS NOT NULL)
// This allows both provider-level defaults and credential-specific overrides
}
model LlmModelCreator {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
name String @unique // e.g., "openai", "anthropic", "meta"
displayName String // e.g., "OpenAI", "Anthropic", "Meta"
description String?
websiteUrl String? // Link to creator's website
logoUrl String? // URL to creator's logo
metadata Json @default("{}")
Models LlmModel[]
}
model LlmModelMigration {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
sourceModelSlug String // The original model that was disabled
targetModelSlug String // The model workflows were migrated to
reason String? // Why the migration happened (e.g., "Provider outage")
// FK constraints ensure slugs reference valid models
SourceModel LlmModel @relation("SourceMigrations", fields: [sourceModelSlug], references: [slug], onDelete: Restrict, onUpdate: Cascade)
TargetModel LlmModel @relation("TargetMigrations", fields: [targetModelSlug], references: [slug], onDelete: Restrict, onUpdate: Cascade)
// Track affected nodes as JSON array of node IDs
// Format: ["node-uuid-1", "node-uuid-2", ...]
migratedNodeIds Json @default("[]")
nodeCount Int // Number of nodes migrated (DB constraint: >= 0)
// Custom pricing override for migrated workflows during the migration period.
// Use case: When migrating users from an expensive model (e.g., GPT-4) to a cheaper
// one (e.g., GPT-3.5), you may want to temporarily maintain the original pricing
// to avoid billing surprises, or offer a discount during the transition.
//
// IMPORTANT: This field is intended for integration with the billing system.
// When billing calculates costs for nodes affected by this migration, it should
// check if customCreditCost is set and use it instead of the target model's cost.
// If null, the target model's normal cost applies.
//
// TODO: Integrate with billing system to apply this override during cost calculation.
// LIMITATION: This is a simple Int and doesn't distinguish RUN vs TOKENS pricing.
// For token-priced models, this may be ambiguous. Consider migrating to a relation
// with LlmModelCost or a dedicated override model in a follow-up PR.
customCreditCost Int? // DB constraint: >= 0 when not null
// Revert tracking
isReverted Boolean @default(false)
revertedAt DateTime?
// Note: Partial unique index in migration SQL prevents multiple active migrations per source:
// UNIQUE (sourceModelSlug) WHERE isReverted = false
@@index([targetModelSlug])
@@index([sourceModelSlug, isReverted]) // Composite index for active migration queries
}