Merge branch 'dev' into swiftyos/secrt-1954-gracefully-disable-feature-request-tools-when-linear_api_key

## Summary
Disables the Print to Console block as requested by Nick Tindle.

## Changes
- Added `disabled=True` to PrintToConsoleBlock in `basic.py`

## Testing
- Block will no longer appear in the platform UI
- Existing graphs using this block should be checked (block ID:
`f3b1c1b2-4c4f-4f0d-8d2f-4c4f0d8d2f4c`)

Closes OPEN-3000

<!-- greptile_comment -->

<h2>Greptile Overview</h2>

<details><summary><h3>Greptile Summary</h3></summary>

Added `disabled=True` parameter to `PrintToConsoleBlock` in `basic.py`
per Nick Tindle's request (OPEN-3000).

- Block follows the same disabling pattern used by other blocks in the
codebase (e.g., `BlockInstallationBlock`, video blocks, Ayrshare blocks)
- Block will no longer appear in the platform UI for new graph creation
- Existing graphs using this block (ID:
`f3b1c1b2-4c4f-4f0d-8d2f-4c4f0d8d2f4c`) will need to be checked for
compatibility
- Comment properly documents the reason for disabling
</details>


<details><summary><h3>Confidence Score: 5/5</h3></summary>

- This PR is safe to merge with minimal risk
- Single-line change that adds a well-documented flag following existing
patterns used throughout the codebase. The change is non-destructive and
only affects UI visibility of the block for new graphs.
- No files require special attention
</details>


<sub>Last reviewed commit: 759003b</sub>

<!-- greptile_other_comments_section -->

<!-- /greptile_comment -->

.github/workflows/claude-ci-failure-auto-fix.yml

@@ -40,6 +40,48 @@ jobs:
           git checkout -b "$BRANCH_NAME"
           echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
 
+      # Backend Python/Poetry setup (so Claude can run linting/tests)
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+
+      - name: Install Poetry
+        run: |
+          cd autogpt_platform/backend
+          HEAD_POETRY_VERSION=$(python3 ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install Python dependencies
+        working-directory: autogpt_platform/backend
+        run: poetry install
+
+      - name: Generate Prisma Client
+        working-directory: autogpt_platform/backend
+        run: poetry run prisma generate && poetry run gen-prisma-stub
+
+      # Frontend Node.js/pnpm setup (so Claude can run linting/tests)
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Install JavaScript dependencies
+        working-directory: autogpt_platform/frontend
+        run: pnpm install --frozen-lockfile
+
       - name: Get CI failure details
         id: failure_details
         uses: actions/github-script@v8

.github/workflows/claude-dependabot.yml

@@ -77,27 +77,15 @@ jobs:
         run: poetry run prisma generate && poetry run gen-prisma-stub
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
+      - name: Enable corepack
+        run: corepack enable
+
       - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set pnpm store directory
-        run: |
-          pnpm config set store-dir ~/.pnpm-store
-          echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
-
-      - name: Cache frontend dependencies
-        uses: actions/cache@v5
-        with:
-          path: ~/.pnpm-store
-          key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install JavaScript dependencies
         working-directory: autogpt_platform/frontend

.github/workflows/claude.yml

@@ -93,27 +93,15 @@ jobs:
         run: poetry run prisma generate && poetry run gen-prisma-stub
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
+      - name: Enable corepack
+        run: corepack enable
+
       - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set pnpm store directory
-        run: |
-          pnpm config set store-dir ~/.pnpm-store
-          echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
-
-      - name: Cache frontend dependencies
-        uses: actions/cache@v5
-        with:
-          path: ~/.pnpm-store
-          key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install JavaScript dependencies
         working-directory: autogpt_platform/frontend

.github/workflows/codeql.yml

@@ -62,7 +62,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -93,6 +93,6 @@ jobs:
         exit 1
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4
       with:
         category: "/language:${{matrix.language}}"

autogpt_platform/backend/.env.default

@@ -104,6 +104,12 @@ TWITTER_CLIENT_SECRET=
 # Make a new workspace for your OAuth APP -- trust me
 # https://linear.app/settings/api/applications/new
 # Callback URL: http://localhost:3000/auth/integrations/oauth_callback
+LINEAR_API_KEY=
+# Linear project and team IDs for the feature request tracker.
+# Find these in your Linear workspace URL: linear.app/<workspace>/project/<project-id>
+# and in team settings. Used by the chat copilot to file and search feature requests.
+LINEAR_FEATURE_REQUEST_PROJECT_ID=
+LINEAR_FEATURE_REQUEST_TEAM_ID=
 LINEAR_CLIENT_ID=
 LINEAR_CLIENT_SECRET=
 

autogpt_platform/backend/backend/api/conn_manager.py

@@ -122,24 +122,6 @@ class ConnectionManager:
 
         return len(connections)
 
-    async def broadcast_to_all(self, *, method: WSMethod, data: dict) -> int:
-        """Broadcast a message to all active websocket connections."""
-        message = WSMessage(
-            method=method,
-            data=data,
-        ).model_dump_json()
-
-        connections = tuple(self.active_connections)
-        if not connections:
-            return 0
-
-        await asyncio.gather(
-            *(connection.send_text(message) for connection in connections),
-            return_exceptions=True,
-        )
-
-        return len(connections)
-
     async def _subscribe(self, channel_key: str, websocket: WebSocket) -> str:
         if channel_key not in self.subscriptions:
             self.subscriptions[channel_key] = set()

autogpt_platform/backend/backend/api/features/admin/execution_analytics_routes.py

@@ -176,64 +176,30 @@ async def get_execution_analytics_config(
         # Return with provider prefix for clarity
         return f"{provider_name}: {model_name}"
 
-    # Get all models from the registry (dynamic, not hardcoded enum)
-    from backend.data import llm_registry
-    from backend.server.v2.llm import db as llm_db
-
-    # Get the recommended model from the database (configurable via admin UI)
-    recommended_model_slug = await llm_db.get_recommended_model_slug()
-
-    # Build the available models list
-    first_enabled_slug = None
-    for registry_model in llm_registry.iter_dynamic_models():
-        # Only include enabled models in the list
-        if not registry_model.is_enabled:
-            continue
-
-        # Track first enabled model as fallback
-        if first_enabled_slug is None:
-            first_enabled_slug = registry_model.slug
-
-        model = LlmModel(registry_model.slug)
+    # Include all LlmModel values (no more filtering by hardcoded list)
+    recommended_model = LlmModel.GPT4O_MINI.value
+    for model in LlmModel:
         label = generate_model_label(model)
         # Add "(Recommended)" suffix to the recommended model
-        if registry_model.slug == recommended_model_slug:
+        if model.value == recommended_model:
             label += " (Recommended)"
 
         available_models.append(
             ModelInfo(
-                value=registry_model.slug,
+                value=model.value,
                 label=label,
-                provider=registry_model.metadata.provider,
+                provider=model.provider,
             )
         )
 
     # Sort models by provider and name for better UX
     available_models.sort(key=lambda x: (x.provider, x.label))
 
-    # Handle case where no models are available
-    if not available_models:
-        logger.warning(
-            "No enabled LLM models found in registry. "
-            "Ensure models are configured and enabled in the LLM Registry."
-        )
-        # Provide a placeholder entry so admins see meaningful feedback
-        available_models.append(
-            ModelInfo(
-                value="",
-                label="No models available - configure in LLM Registry",
-                provider="none",
-            )
-        )
-
-    # Use the DB recommended model, or fallback to first enabled model
-    final_recommended = recommended_model_slug or first_enabled_slug or ""
-
     return ExecutionAnalyticsConfig(
         available_models=available_models,
         default_system_prompt=DEFAULT_SYSTEM_PROMPT,
         default_user_prompt=DEFAULT_USER_PROMPT,
-        recommended_model=final_recommended,
+        recommended_model=recommended_model,
     )
 
 

autogpt_platform/backend/backend/api/features/admin/llm_routes.py

@@ -1,593 +0,0 @@
-import logging
-
-import autogpt_libs.auth
-import fastapi
-
-from backend.data import llm_registry
-from backend.data.block_cost_config import refresh_llm_costs
-from backend.server.v2.llm import db as llm_db
-from backend.server.v2.llm import model as llm_model
-
-logger = logging.getLogger(__name__)
-
-router = fastapi.APIRouter(
-    tags=["llm", "admin"],
-    dependencies=[fastapi.Security(autogpt_libs.auth.requires_admin_user)],
-)
-
-
-async def _refresh_runtime_state() -> None:
-    """Refresh the LLM registry and clear all related caches to ensure real-time updates."""
-    logger.info("Refreshing LLM registry runtime state...")
-    try:
-        # Refresh registry from database
-        await llm_registry.refresh_llm_registry()
-        await refresh_llm_costs()
-
-        # Clear block schema caches so they're regenerated with updated model options
-        from backend.blocks._base import BlockSchema
-
-        BlockSchema.clear_all_schema_caches()
-        logger.info("Cleared all block schema caches")
-
-        # Clear the /blocks endpoint cache so frontend gets updated schemas
-        try:
-            from backend.api.features.v1 import _get_cached_blocks
-
-            _get_cached_blocks.cache_clear()
-            logger.info("Cleared /blocks endpoint cache")
-        except Exception as e:
-            logger.warning("Failed to clear /blocks cache: %s", e)
-
-        # Clear the v2 builder caches
-        try:
-            from backend.api.features.builder import db as builder_db
-
-            builder_db._get_all_providers.cache_clear()
-            logger.info("Cleared v2 builder providers cache")
-            builder_db._build_cached_search_results.cache_clear()
-            logger.info("Cleared v2 builder search results cache")
-        except Exception as e:
-            logger.debug("Could not clear v2 builder cache: %s", e)
-
-        # Notify all executor services to refresh their registry cache
-        from backend.data.llm_registry import publish_registry_refresh_notification
-
-        await publish_registry_refresh_notification()
-        logger.info("Published registry refresh notification")
-    except Exception as exc:
-        logger.exception(
-            "LLM runtime state refresh failed; caches may be stale: %s", exc
-        )
-
-
-@router.get(
-    "/providers",
-    summary="List LLM providers",
-    response_model=llm_model.LlmProvidersResponse,
-)
-async def list_llm_providers(include_models: bool = True):
-    providers = await llm_db.list_providers(include_models=include_models)
-    return llm_model.LlmProvidersResponse(providers=providers)
-
-
-@router.post(
-    "/providers",
-    summary="Create LLM provider",
-    response_model=llm_model.LlmProvider,
-)
-async def create_llm_provider(request: llm_model.UpsertLlmProviderRequest):
-    provider = await llm_db.upsert_provider(request=request)
-    await _refresh_runtime_state()
-    return provider
-
-
-@router.patch(
-    "/providers/{provider_id}",
-    summary="Update LLM provider",
-    response_model=llm_model.LlmProvider,
-)
-async def update_llm_provider(
-    provider_id: str,
-    request: llm_model.UpsertLlmProviderRequest,
-):
-    provider = await llm_db.upsert_provider(request=request, provider_id=provider_id)
-    await _refresh_runtime_state()
-    return provider
-
-
-@router.delete(
-    "/providers/{provider_id}",
-    summary="Delete LLM provider",
-    response_model=dict,
-)
-async def delete_llm_provider(provider_id: str):
-    """
-    Delete an LLM provider.
-
-    A provider can only be deleted if it has no associated models.
-    Delete all models from the provider first before deleting the provider.
-    """
-    try:
-        await llm_db.delete_provider(provider_id)
-        await _refresh_runtime_state()
-        logger.info("Deleted LLM provider '%s'", provider_id)
-        return {"success": True, "message": "Provider deleted successfully"}
-    except ValueError as e:
-        logger.warning("Failed to delete provider '%s': %s", provider_id, e)
-        raise fastapi.HTTPException(status_code=400, detail=str(e))
-    except Exception as e:
-        logger.exception("Failed to delete provider '%s': %s", provider_id, e)
-        raise fastapi.HTTPException(status_code=500, detail=str(e))
-
-
-@router.get(
-    "/models",
-    summary="List LLM models",
-    response_model=llm_model.LlmModelsResponse,
-)
-async def list_llm_models(
-    provider_id: str | None = fastapi.Query(default=None),
-    page: int = fastapi.Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = fastapi.Query(
-        default=50, ge=1, le=100, description="Number of models per page"
-    ),
-):
-    return await llm_db.list_models(
-        provider_id=provider_id, page=page, page_size=page_size
-    )
-
-
-@router.post(
-    "/models",
-    summary="Create LLM model",
-    response_model=llm_model.LlmModel,
-)
-async def create_llm_model(request: llm_model.CreateLlmModelRequest):
-    model = await llm_db.create_model(request=request)
-    await _refresh_runtime_state()
-    return model
-
-
-@router.patch(
-    "/models/{model_id}",
-    summary="Update LLM model",
-    response_model=llm_model.LlmModel,
-)
-async def update_llm_model(
-    model_id: str,
-    request: llm_model.UpdateLlmModelRequest,
-):
-    model = await llm_db.update_model(model_id=model_id, request=request)
-    await _refresh_runtime_state()
-    return model
-
-
-@router.patch(
-    "/models/{model_id}/toggle",
-    summary="Toggle LLM model availability",
-    response_model=llm_model.ToggleLlmModelResponse,
-)
-async def toggle_llm_model(
-    model_id: str,
-    request: llm_model.ToggleLlmModelRequest,
-):
-    """
-    Toggle a model's enabled status, optionally migrating workflows when disabling.
-
-    If disabling a model and `migrate_to_slug` is provided, all workflows using
-    this model will be migrated to the specified replacement model before disabling.
-    A migration record is created which can be reverted later using the revert endpoint.
-
-    Optional fields:
-    - `migration_reason`: Reason for the migration (e.g., "Provider outage")
-    - `custom_credit_cost`: Custom pricing override for billing during migration
-    """
-    try:
-        result = await llm_db.toggle_model(
-            model_id=model_id,
-            is_enabled=request.is_enabled,
-            migrate_to_slug=request.migrate_to_slug,
-            migration_reason=request.migration_reason,
-            custom_credit_cost=request.custom_credit_cost,
-        )
-        await _refresh_runtime_state()
-        if result.nodes_migrated > 0:
-            logger.info(
-                "Toggled model '%s' to %s and migrated %d nodes to '%s' (migration_id=%s)",
-                result.model.slug,
-                "enabled" if request.is_enabled else "disabled",
-                result.nodes_migrated,
-                result.migrated_to_slug,
-                result.migration_id,
-            )
-        return result
-    except ValueError as exc:
-        logger.warning("Model toggle validation failed: %s", exc)
-        raise fastapi.HTTPException(status_code=400, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to toggle LLM model %s: %s", model_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to toggle model availability",
-        ) from exc
-
-
-@router.get(
-    "/models/{model_id}/usage",
-    summary="Get model usage count",
-    response_model=llm_model.LlmModelUsageResponse,
-)
-async def get_llm_model_usage(model_id: str):
-    """Get the number of workflow nodes using this model."""
-    try:
-        return await llm_db.get_model_usage(model_id=model_id)
-    except ValueError as exc:
-        raise fastapi.HTTPException(status_code=404, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to get model usage %s: %s", model_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to get model usage",
-        ) from exc
-
-
-@router.delete(
-    "/models/{model_id}",
-    summary="Delete LLM model and migrate workflows",
-    response_model=llm_model.DeleteLlmModelResponse,
-)
-async def delete_llm_model(
-    model_id: str,
-    replacement_model_slug: str | None = fastapi.Query(
-        default=None,
-        description="Slug of the model to migrate existing workflows to (required only if workflows use this model)",
-    ),
-):
-    """
-    Delete a model and optionally migrate workflows using it to a replacement model.
-
-    If no workflows are using this model, it can be deleted without providing a
-    replacement. If workflows exist, replacement_model_slug is required.
-
-    This endpoint:
-    1. Counts how many workflow nodes use the model being deleted
-    2. If nodes exist, validates the replacement model and migrates them
-    3. Deletes the model record
-    4. Refreshes all caches and notifies executors
-
-    Example: DELETE /api/llm/admin/models/{id}?replacement_model_slug=gpt-4o
-    Example (no usage): DELETE /api/llm/admin/models/{id}
-    """
-    try:
-        result = await llm_db.delete_model(
-            model_id=model_id, replacement_model_slug=replacement_model_slug
-        )
-        await _refresh_runtime_state()
-        logger.info(
-            "Deleted model '%s' and migrated %d nodes to '%s'",
-            result.deleted_model_slug,
-            result.nodes_migrated,
-            result.replacement_model_slug,
-        )
-        return result
-    except ValueError as exc:
-        # Validation errors (model not found, replacement invalid, etc.)
-        logger.warning("Model deletion validation failed: %s", exc)
-        raise fastapi.HTTPException(status_code=400, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to delete LLM model %s: %s", model_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to delete model and migrate workflows",
-        ) from exc
-
-
-# ============================================================================
-# Migration Management Endpoints
-# ============================================================================
-
-
-@router.get(
-    "/migrations",
-    summary="List model migrations",
-    response_model=llm_model.LlmMigrationsResponse,
-)
-async def list_llm_migrations(
-    include_reverted: bool = fastapi.Query(
-        default=False, description="Include reverted migrations in the list"
-    ),
-):
-    """
-    List all model migrations.
-
-    Migrations are created when disabling a model with the migrate_to_slug option.
-    They can be reverted to restore the original model configuration.
-    """
-    try:
-        migrations = await llm_db.list_migrations(include_reverted=include_reverted)
-        return llm_model.LlmMigrationsResponse(migrations=migrations)
-    except Exception as exc:
-        logger.exception("Failed to list migrations: %s", exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to list migrations",
-        ) from exc
-
-
-@router.get(
-    "/migrations/{migration_id}",
-    summary="Get migration details",
-    response_model=llm_model.LlmModelMigration,
-)
-async def get_llm_migration(migration_id: str):
-    """Get details of a specific migration."""
-    try:
-        migration = await llm_db.get_migration(migration_id)
-        if not migration:
-            raise fastapi.HTTPException(
-                status_code=404, detail=f"Migration '{migration_id}' not found"
-            )
-        return migration
-    except fastapi.HTTPException:
-        raise
-    except Exception as exc:
-        logger.exception("Failed to get migration %s: %s", migration_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to get migration",
-        ) from exc
-
-
-@router.post(
-    "/migrations/{migration_id}/revert",
-    summary="Revert a model migration",
-    response_model=llm_model.RevertMigrationResponse,
-)
-async def revert_llm_migration(
-    migration_id: str,
-    request: llm_model.RevertMigrationRequest | None = None,
-):
-    """
-    Revert a model migration, restoring affected workflows to their original model.
-
-    This only reverts the specific nodes that were part of the migration.
-    The source model must exist for the revert to succeed.
-
-    Options:
-    - `re_enable_source_model`: Whether to re-enable the source model if disabled (default: True)
-
-    Response includes:
-    - `nodes_reverted`: Number of nodes successfully reverted
-    - `nodes_already_changed`: Number of nodes that were modified since migration (not reverted)
-    - `source_model_re_enabled`: Whether the source model was re-enabled
-
-    Requirements:
-    - Migration must not already be reverted
-    - Source model must exist
-    """
-    try:
-        re_enable = request.re_enable_source_model if request else True
-        result = await llm_db.revert_migration(
-            migration_id,
-            re_enable_source_model=re_enable,
-        )
-        await _refresh_runtime_state()
-        logger.info(
-            "Reverted migration '%s': %d nodes restored from '%s' to '%s' "
-            "(%d already changed, source re-enabled=%s)",
-            migration_id,
-            result.nodes_reverted,
-            result.target_model_slug,
-            result.source_model_slug,
-            result.nodes_already_changed,
-            result.source_model_re_enabled,
-        )
-        return result
-    except ValueError as exc:
-        logger.warning("Migration revert validation failed: %s", exc)
-        raise fastapi.HTTPException(status_code=400, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to revert migration %s: %s", migration_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to revert migration",
-        ) from exc
-
-
-# ============================================================================
-# Creator Management Endpoints
-# ============================================================================
-
-
-@router.get(
-    "/creators",
-    summary="List model creators",
-    response_model=llm_model.LlmCreatorsResponse,
-)
-async def list_llm_creators():
-    """
-    List all model creators.
-
-    Creators are organizations that create/train models (e.g., OpenAI, Meta, Anthropic).
-    This is distinct from providers who host/serve the models (e.g., OpenRouter).
-    """
-    try:
-        creators = await llm_db.list_creators()
-        return llm_model.LlmCreatorsResponse(creators=creators)
-    except Exception as exc:
-        logger.exception("Failed to list creators: %s", exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to list creators",
-        ) from exc
-
-
-@router.get(
-    "/creators/{creator_id}",
-    summary="Get creator details",
-    response_model=llm_model.LlmModelCreator,
-)
-async def get_llm_creator(creator_id: str):
-    """Get details of a specific model creator."""
-    try:
-        creator = await llm_db.get_creator(creator_id)
-        if not creator:
-            raise fastapi.HTTPException(
-                status_code=404, detail=f"Creator '{creator_id}' not found"
-            )
-        return creator
-    except fastapi.HTTPException:
-        raise
-    except Exception as exc:
-        logger.exception("Failed to get creator %s: %s", creator_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to get creator",
-        ) from exc
-
-
-@router.post(
-    "/creators",
-    summary="Create model creator",
-    response_model=llm_model.LlmModelCreator,
-)
-async def create_llm_creator(request: llm_model.UpsertLlmCreatorRequest):
-    """
-    Create a new model creator.
-
-    A creator represents an organization that creates/trains AI models,
-    such as OpenAI, Anthropic, Meta, or Google.
-    """
-    try:
-        creator = await llm_db.upsert_creator(request=request)
-        await _refresh_runtime_state()
-        logger.info("Created model creator '%s' (%s)", creator.display_name, creator.id)
-        return creator
-    except Exception as exc:
-        logger.exception("Failed to create creator: %s", exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to create creator",
-        ) from exc
-
-
-@router.patch(
-    "/creators/{creator_id}",
-    summary="Update model creator",
-    response_model=llm_model.LlmModelCreator,
-)
-async def update_llm_creator(
-    creator_id: str,
-    request: llm_model.UpsertLlmCreatorRequest,
-):
-    """Update an existing model creator."""
-    try:
-        creator = await llm_db.upsert_creator(request=request, creator_id=creator_id)
-        await _refresh_runtime_state()
-        logger.info("Updated model creator '%s' (%s)", creator.display_name, creator_id)
-        return creator
-    except Exception as exc:
-        logger.exception("Failed to update creator %s: %s", creator_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to update creator",
-        ) from exc
-
-
-@router.delete(
-    "/creators/{creator_id}",
-    summary="Delete model creator",
-    response_model=dict,
-)
-async def delete_llm_creator(creator_id: str):
-    """
-    Delete a model creator.
-
-    This will remove the creator association from all models that reference it
-    (sets creatorId to NULL), but will not delete the models themselves.
-    """
-    try:
-        await llm_db.delete_creator(creator_id)
-        await _refresh_runtime_state()
-        logger.info("Deleted model creator '%s'", creator_id)
-        return {"success": True, "message": f"Creator '{creator_id}' deleted"}
-    except ValueError as exc:
-        logger.warning("Creator deletion validation failed: %s", exc)
-        raise fastapi.HTTPException(status_code=404, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to delete creator %s: %s", creator_id, exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to delete creator",
-        ) from exc
-
-
-# ============================================================================
-# Recommended Model Endpoints
-# ============================================================================
-
-
-@router.get(
-    "/recommended-model",
-    summary="Get recommended model",
-    response_model=llm_model.RecommendedModelResponse,
-)
-async def get_recommended_model():
-    """
-    Get the currently recommended LLM model.
-
-    The recommended model is shown to users as the default/suggested option
-    in model selection dropdowns.
-    """
-    try:
-        model = await llm_db.get_recommended_model()
-        return llm_model.RecommendedModelResponse(
-            model=model,
-            slug=model.slug if model else None,
-        )
-    except Exception as exc:
-        logger.exception("Failed to get recommended model: %s", exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to get recommended model",
-        ) from exc
-
-
-@router.post(
-    "/recommended-model",
-    summary="Set recommended model",
-    response_model=llm_model.SetRecommendedModelResponse,
-)
-async def set_recommended_model(request: llm_model.SetRecommendedModelRequest):
-    """
-    Set a model as the recommended model.
-
-    This clears the recommended flag from any other model and sets it on
-    the specified model. The model must be enabled to be set as recommended.
-
-    The recommended model is displayed to users as the default/suggested
-    option in model selection dropdowns throughout the platform.
-    """
-    try:
-        model, previous_slug = await llm_db.set_recommended_model(request.model_id)
-        await _refresh_runtime_state()
-        logger.info(
-            "Set recommended model to '%s' (previous: %s)",
-            model.slug,
-            previous_slug or "none",
-        )
-        return llm_model.SetRecommendedModelResponse(
-            model=model,
-            previous_recommended_slug=previous_slug,
-            message=f"Model '{model.display_name}' is now the recommended model",
-        )
-    except ValueError as exc:
-        logger.warning("Set recommended model validation failed: %s", exc)
-        raise fastapi.HTTPException(status_code=400, detail=str(exc)) from exc
-    except Exception as exc:
-        logger.exception("Failed to set recommended model: %s", exc)
-        raise fastapi.HTTPException(
-            status_code=500,
-            detail="Failed to set recommended model",
-        ) from exc

autogpt_platform/backend/backend/api/features/admin/llm_routes_test.py

@@ -1,491 +0,0 @@
-import json
-from unittest.mock import AsyncMock
-
-import fastapi
-import fastapi.testclient
-import pytest
-import pytest_mock
-from autogpt_libs.auth.jwt_utils import get_jwt_payload
-from pytest_snapshot.plugin import Snapshot
-
-import backend.api.features.admin.llm_routes as llm_routes
-from backend.server.v2.llm import model as llm_model
-from backend.util.models import Pagination
-
-app = fastapi.FastAPI()
-app.include_router(llm_routes.router, prefix="/admin/llm")
-
-client = fastapi.testclient.TestClient(app)
-
-
-@pytest.fixture(autouse=True)
-def setup_app_admin_auth(mock_jwt_admin):
-    """Setup admin auth overrides for all tests in this module"""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_admin["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def test_list_llm_providers_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful listing of LLM providers"""
-    # Mock the database function
-    mock_providers = [
-        {
-            "id": "provider-1",
-            "name": "openai",
-            "display_name": "OpenAI",
-            "description": "OpenAI LLM provider",
-            "supports_tools": True,
-            "supports_json_output": True,
-            "supports_reasoning": False,
-            "supports_parallel_tool": True,
-            "metadata": {},
-            "models": [],
-        },
-        {
-            "id": "provider-2",
-            "name": "anthropic",
-            "display_name": "Anthropic",
-            "description": "Anthropic LLM provider",
-            "supports_tools": True,
-            "supports_json_output": True,
-            "supports_reasoning": False,
-            "supports_parallel_tool": True,
-            "metadata": {},
-            "models": [],
-        },
-    ]
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.list_providers",
-        new=AsyncMock(return_value=mock_providers),
-    )
-
-    response = client.get("/admin/llm/providers")
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert len(response_data["providers"]) == 2
-    assert response_data["providers"][0]["name"] == "openai"
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "list_llm_providers_success.json",
-    )
-
-
-def test_list_llm_models_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful listing of LLM models with pagination"""
-    # Mock the database function - now returns LlmModelsResponse
-    mock_model = llm_model.LlmModel(
-        id="model-1",
-        slug="gpt-4o",
-        display_name="GPT-4o",
-        description="GPT-4 Optimized",
-        provider_id="provider-1",
-        context_window=128000,
-        max_output_tokens=16384,
-        is_enabled=True,
-        capabilities={},
-        metadata={},
-        costs=[
-            llm_model.LlmModelCost(
-                id="cost-1",
-                credit_cost=10,
-                credential_provider="openai",
-                metadata={},
-            )
-        ],
-    )
-
-    mock_response = llm_model.LlmModelsResponse(
-        models=[mock_model],
-        pagination=Pagination(
-            total_items=1,
-            total_pages=1,
-            current_page=1,
-            page_size=50,
-        ),
-    )
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.list_models",
-        new=AsyncMock(return_value=mock_response),
-    )
-
-    response = client.get("/admin/llm/models")
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert len(response_data["models"]) == 1
-    assert response_data["models"][0]["slug"] == "gpt-4o"
-    assert response_data["pagination"]["total_items"] == 1
-    assert response_data["pagination"]["page_size"] == 50
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "list_llm_models_success.json",
-    )
-
-
-def test_create_llm_provider_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful creation of LLM provider"""
-    mock_provider = {
-        "id": "new-provider-id",
-        "name": "groq",
-        "display_name": "Groq",
-        "description": "Groq LLM provider",
-        "supports_tools": True,
-        "supports_json_output": True,
-        "supports_reasoning": False,
-        "supports_parallel_tool": False,
-        "metadata": {},
-    }
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.upsert_provider",
-        new=AsyncMock(return_value=mock_provider),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    request_data = {
-        "name": "groq",
-        "display_name": "Groq",
-        "description": "Groq LLM provider",
-        "supports_tools": True,
-        "supports_json_output": True,
-        "supports_reasoning": False,
-        "supports_parallel_tool": False,
-        "metadata": {},
-    }
-
-    response = client.post("/admin/llm/providers", json=request_data)
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["name"] == "groq"
-    assert response_data["display_name"] == "Groq"
-
-    # Verify refresh was called
-    mock_refresh.assert_called_once()
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "create_llm_provider_success.json",
-    )
-
-
-def test_create_llm_model_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful creation of LLM model"""
-    mock_model = {
-        "id": "new-model-id",
-        "slug": "gpt-4.1-mini",
-        "display_name": "GPT-4.1 Mini",
-        "description": "Latest GPT-4.1 Mini model",
-        "provider_id": "provider-1",
-        "context_window": 128000,
-        "max_output_tokens": 16384,
-        "is_enabled": True,
-        "capabilities": {},
-        "metadata": {},
-        "costs": [
-            {
-                "id": "cost-id",
-                "credit_cost": 5,
-                "credential_provider": "openai",
-                "metadata": {},
-            }
-        ],
-    }
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.create_model",
-        new=AsyncMock(return_value=mock_model),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    request_data = {
-        "slug": "gpt-4.1-mini",
-        "display_name": "GPT-4.1 Mini",
-        "description": "Latest GPT-4.1 Mini model",
-        "provider_id": "provider-1",
-        "context_window": 128000,
-        "max_output_tokens": 16384,
-        "is_enabled": True,
-        "capabilities": {},
-        "metadata": {},
-        "costs": [
-            {
-                "credit_cost": 5,
-                "credential_provider": "openai",
-                "metadata": {},
-            }
-        ],
-    }
-
-    response = client.post("/admin/llm/models", json=request_data)
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["slug"] == "gpt-4.1-mini"
-    assert response_data["is_enabled"] is True
-
-    # Verify refresh was called
-    mock_refresh.assert_called_once()
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "create_llm_model_success.json",
-    )
-
-
-def test_update_llm_model_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful update of LLM model"""
-    mock_model = {
-        "id": "model-1",
-        "slug": "gpt-4o",
-        "display_name": "GPT-4o Updated",
-        "description": "Updated description",
-        "provider_id": "provider-1",
-        "context_window": 256000,
-        "max_output_tokens": 32768,
-        "is_enabled": True,
-        "capabilities": {},
-        "metadata": {},
-        "costs": [
-            {
-                "id": "cost-1",
-                "credit_cost": 15,
-                "credential_provider": "openai",
-                "metadata": {},
-            }
-        ],
-    }
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.update_model",
-        new=AsyncMock(return_value=mock_model),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    request_data = {
-        "display_name": "GPT-4o Updated",
-        "description": "Updated description",
-        "context_window": 256000,
-        "max_output_tokens": 32768,
-    }
-
-    response = client.patch("/admin/llm/models/model-1", json=request_data)
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["display_name"] == "GPT-4o Updated"
-    assert response_data["context_window"] == 256000
-
-    # Verify refresh was called
-    mock_refresh.assert_called_once()
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "update_llm_model_success.json",
-    )
-
-
-def test_toggle_llm_model_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful toggling of LLM model enabled status"""
-    # Create a proper mock model object
-    mock_model = llm_model.LlmModel(
-        id="model-1",
-        slug="gpt-4o",
-        display_name="GPT-4o",
-        description="GPT-4 Optimized",
-        provider_id="provider-1",
-        context_window=128000,
-        max_output_tokens=16384,
-        is_enabled=False,
-        capabilities={},
-        metadata={},
-        costs=[],
-    )
-
-    # Create a proper ToggleLlmModelResponse
-    mock_response = llm_model.ToggleLlmModelResponse(
-        model=mock_model,
-        nodes_migrated=0,
-        migrated_to_slug=None,
-        migration_id=None,
-    )
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.toggle_model",
-        new=AsyncMock(return_value=mock_response),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    request_data = {"is_enabled": False}
-
-    response = client.patch("/admin/llm/models/model-1/toggle", json=request_data)
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["model"]["is_enabled"] is False
-
-    # Verify refresh was called
-    mock_refresh.assert_called_once()
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "toggle_llm_model_success.json",
-    )
-
-
-def test_delete_llm_model_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test successful deletion of LLM model with migration"""
-    # Create a proper DeleteLlmModelResponse
-    mock_response = llm_model.DeleteLlmModelResponse(
-        deleted_model_slug="gpt-3.5-turbo",
-        deleted_model_display_name="GPT-3.5 Turbo",
-        replacement_model_slug="gpt-4o-mini",
-        nodes_migrated=42,
-        message="Successfully deleted model 'GPT-3.5 Turbo' (gpt-3.5-turbo) "
-        "and migrated 42 workflow node(s) to 'gpt-4o-mini'.",
-    )
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.delete_model",
-        new=AsyncMock(return_value=mock_response),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    response = client.delete(
-        "/admin/llm/models/model-1?replacement_model_slug=gpt-4o-mini"
-    )
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["deleted_model_slug"] == "gpt-3.5-turbo"
-    assert response_data["nodes_migrated"] == 42
-    assert response_data["replacement_model_slug"] == "gpt-4o-mini"
-
-    # Verify refresh was called
-    mock_refresh.assert_called_once()
-
-    # Snapshot test the response (must be string)
-    configured_snapshot.assert_match(
-        json.dumps(response_data, indent=2, sort_keys=True),
-        "delete_llm_model_success.json",
-    )
-
-
-def test_delete_llm_model_validation_error(
-    mocker: pytest_mock.MockFixture,
-) -> None:
-    """Test deletion fails with proper error when validation fails"""
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.delete_model",
-        new=AsyncMock(side_effect=ValueError("Replacement model 'invalid' not found")),
-    )
-
-    response = client.delete("/admin/llm/models/model-1?replacement_model_slug=invalid")
-
-    assert response.status_code == 400
-    assert "Replacement model 'invalid' not found" in response.json()["detail"]
-
-
-def test_delete_llm_model_no_replacement_with_usage(
-    mocker: pytest_mock.MockFixture,
-) -> None:
-    """Test deletion fails when nodes exist but no replacement is provided"""
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.delete_model",
-        new=AsyncMock(
-            side_effect=ValueError(
-                "Cannot delete model 'test-model': 5 workflow node(s) are using it. "
-                "Please provide a replacement_model_slug to migrate them."
-            )
-        ),
-    )
-
-    response = client.delete("/admin/llm/models/model-1")
-
-    assert response.status_code == 400
-    assert "workflow node(s) are using it" in response.json()["detail"]
-
-
-def test_delete_llm_model_no_replacement_no_usage(
-    mocker: pytest_mock.MockFixture,
-) -> None:
-    """Test deletion succeeds when no nodes use the model and no replacement is provided"""
-    mock_response = llm_model.DeleteLlmModelResponse(
-        deleted_model_slug="unused-model",
-        deleted_model_display_name="Unused Model",
-        replacement_model_slug=None,
-        nodes_migrated=0,
-        message="Successfully deleted model 'Unused Model' (unused-model). No workflows were using this model.",
-    )
-
-    mocker.patch(
-        "backend.api.features.admin.llm_routes.llm_db.delete_model",
-        new=AsyncMock(return_value=mock_response),
-    )
-
-    mock_refresh = mocker.patch(
-        "backend.api.features.admin.llm_routes._refresh_runtime_state",
-        new=AsyncMock(),
-    )
-
-    response = client.delete("/admin/llm/models/model-1")
-
-    assert response.status_code == 200
-    response_data = response.json()
-    assert response_data["deleted_model_slug"] == "unused-model"
-    assert response_data["nodes_migrated"] == 0
-    assert response_data["replacement_model_slug"] is None
-    mock_refresh.assert_called_once()

autogpt_platform/backend/backend/api/features/builder/db.py

@@ -20,7 +20,6 @@ from backend.blocks._base import (
 )
 from backend.blocks.llm import LlmModel
 from backend.data.db import query_raw_with_schema
-from backend.data.llm_registry import get_all_model_slugs_for_validation
 from backend.integrations.providers import ProviderName
 from backend.util.cache import cached
 from backend.util.models import Pagination
@@ -37,14 +36,7 @@ from .model import (
 )
 
 logger = logging.getLogger(__name__)
-
-
-def _get_llm_models() -> list[str]:
-    """Get LLM model names for search matching from the registry."""
-    return [
-        slug.lower().replace("-", " ") for slug in get_all_model_slugs_for_validation()
-    ]
-
+llm_models = [name.name.lower().replace("_", " ") for name in LlmModel]
 
 MAX_LIBRARY_AGENT_RESULTS = 100
 MAX_MARKETPLACE_AGENT_RESULTS = 100
@@ -509,10 +501,8 @@ async def _get_static_counts():
 def _matches_llm_model(schema_cls: type[BlockSchema], query: str) -> bool:
     for field in schema_cls.model_fields.values():
         if field.annotation == LlmModel:
-            # Normalize query same as model slugs (lowercase, hyphens to spaces)
-            normalized_model_query = query.lower().replace("-", " ")
-            # Check if query matches any value in llm_models from registry
-            if any(normalized_model_query in name for name in _get_llm_models()):
+            # Check if query matches any value in llm_models
+            if any(query in name for name in llm_models):
                 return True
     return False
 

autogpt_platform/backend/backend/api/features/chat/service.py

@@ -1245,6 +1245,7 @@ async def _stream_chat_chunks(
                 return
             except Exception as e:
                 last_error = e
+
                 if _is_retryable_error(e) and retry_count < MAX_RETRIES:
                     retry_count += 1
                     # Calculate delay with exponential backoff
@@ -1260,12 +1261,27 @@ async def _stream_chat_chunks(
                     continue  # Retry the stream
                 else:
                     # Non-retryable error or max retries exceeded
-                    logger.error(
-                        f"Error in stream (not retrying): {e!s}",
-                        exc_info=True,
+                    _log_api_error(
+                        error=e,
+                        context="stream (not retrying)",
+                        session_id=session.session_id if session else None,
+                        message_count=len(messages) if messages else None,
+                        model=model,
+                        retry_count=retry_count,
                     )
                     error_code = None
                     error_text = str(e)
+
+                    error_details = _extract_api_error_details(e)
+                    if error_details.get("response_body"):
+                        body = error_details["response_body"]
+                        if isinstance(body, dict):
+                            err = body.get("error")
+                            if isinstance(err, dict) and err.get("message"):
+                                error_text = err["message"]
+                            elif body.get("message"):
+                                error_text = body["message"]
+
                     if _is_region_blocked_error(e):
                         error_code = "MODEL_NOT_AVAILABLE_REGION"
                         error_text = (
@@ -1282,9 +1298,13 @@ async def _stream_chat_chunks(
 
         # If we exit the retry loop without returning, it means we exhausted retries
         if last_error:
-            logger.error(
-                f"Max retries ({MAX_RETRIES}) exceeded. Last error: {last_error!s}",
-                exc_info=True,
+            _log_api_error(
+                error=last_error,
+                context=f"stream (max retries {MAX_RETRIES} exceeded)",
+                session_id=session.session_id if session else None,
+                message_count=len(messages) if messages else None,
+                model=model,
+                retry_count=MAX_RETRIES,
             )
             yield StreamError(errorText=f"Max retries exceeded: {last_error!s}")
             yield StreamFinish()
@@ -1857,6 +1877,7 @@ async def _generate_llm_continuation(
                 break  # Success, exit retry loop
             except Exception as e:
                 last_error = e
+
                 if _is_retryable_error(e) and retry_count < MAX_RETRIES:
                     retry_count += 1
                     delay = min(
@@ -1870,17 +1891,25 @@ async def _generate_llm_continuation(
                     await asyncio.sleep(delay)
                     continue
                 else:
-                    # Non-retryable error - log and exit gracefully
-                    logger.error(
-                        f"Non-retryable error in LLM continuation: {e!s}",
-                        exc_info=True,
+                    # Non-retryable error - log details and exit gracefully
+                    _log_api_error(
+                        error=e,
+                        context="LLM continuation (not retrying)",
+                        session_id=session_id,
+                        message_count=len(messages) if messages else None,
+                        model=config.model,
+                        retry_count=retry_count,
                     )
                     return
 
         if last_error:
-            logger.error(
-                f"Max retries ({MAX_RETRIES}) exceeded for LLM continuation. "
-                f"Last error: {last_error!s}"
+            _log_api_error(
+                error=last_error,
+                context=f"LLM continuation (max retries {MAX_RETRIES} exceeded)",
+                session_id=session_id,
+                message_count=len(messages) if messages else None,
+                model=config.model,
+                retry_count=MAX_RETRIES,
             )
             return
 
@@ -1920,6 +1949,91 @@ async def _generate_llm_continuation(
         logger.error(f"Failed to generate LLM continuation: {e}", exc_info=True)
 
 
+def _log_api_error(
+    error: Exception,
+    context: str,
+    session_id: str | None = None,
+    message_count: int | None = None,
+    model: str | None = None,
+    retry_count: int = 0,
+) -> None:
+    """Log detailed API error information for debugging."""
+    details = _extract_api_error_details(error)
+    details["context"] = context
+    details["session_id"] = session_id
+    details["message_count"] = message_count
+    details["model"] = model
+    details["retry_count"] = retry_count
+
+    if isinstance(error, RateLimitError):
+        logger.warning(f"Rate limit error in {context}: {details}", exc_info=error)
+    elif isinstance(error, APIConnectionError):
+        logger.warning(f"API connection error in {context}: {details}", exc_info=error)
+    elif isinstance(error, APIStatusError) and error.status_code >= 500:
+        logger.error(f"API server error (5xx) in {context}: {details}", exc_info=error)
+    else:
+        logger.error(f"API error in {context}: {details}", exc_info=error)
+
+
+def _extract_api_error_details(error: Exception) -> dict[str, Any]:
+    """Extract detailed information from OpenAI/OpenRouter API errors."""
+    error_msg = str(error)
+    details: dict[str, Any] = {
+        "error_type": type(error).__name__,
+        "error_message": error_msg[:500] + "..." if len(error_msg) > 500 else error_msg,
+    }
+
+    if hasattr(error, "code"):
+        details["code"] = getattr(error, "code", None)
+    if hasattr(error, "param"):
+        details["param"] = getattr(error, "param", None)
+
+    if isinstance(error, APIStatusError):
+        details["status_code"] = error.status_code
+        details["request_id"] = getattr(error, "request_id", None)
+
+        if hasattr(error, "body") and error.body:
+            details["response_body"] = _sanitize_error_body(error.body)
+
+        if hasattr(error, "response") and error.response:
+            headers = error.response.headers
+            details["openrouter_provider"] = headers.get("x-openrouter-provider")
+            details["openrouter_model"] = headers.get("x-openrouter-model")
+            details["retry_after"] = headers.get("retry-after")
+            details["rate_limit_remaining"] = headers.get("x-ratelimit-remaining")
+
+    return details
+
+
+def _sanitize_error_body(
+    body: Any, max_length: int = 2000
+) -> dict[str, Any] | str | None:
+    """Extract only safe fields from error response body to avoid logging sensitive data."""
+    if not isinstance(body, dict):
+        # Non-dict bodies (e.g., HTML error pages) - return truncated string
+        if body is not None:
+            body_str = str(body)
+            if len(body_str) > max_length:
+                return body_str[:max_length] + "...[truncated]"
+            return body_str
+        return None
+
+    safe_fields = ("message", "type", "code", "param", "error")
+    sanitized: dict[str, Any] = {}
+
+    for field in safe_fields:
+        if field in body:
+            value = body[field]
+            if field == "error" and isinstance(value, dict):
+                sanitized[field] = _sanitize_error_body(value, max_length)
+            elif isinstance(value, str) and len(value) > max_length:
+                sanitized[field] = value[:max_length] + "...[truncated]"
+            else:
+                sanitized[field] = value
+
+    return sanitized if sanitized else None
+
+
 async def _generate_llm_continuation_with_streaming(
     session_id: str,
     user_id: str | None,

autogpt_platform/backend/backend/api/features/chat/tools/__init__.py

@@ -52,6 +52,38 @@ TOOL_REGISTRY: dict[str, BaseTool] = {
     "delete_workspace_file": DeleteWorkspaceFileTool(),
 }
 
+
+def _register_feature_request_tools() -> None:
+    """Register feature request tools only if Linear configuration is available."""
+    from backend.util.settings import Settings
+
+    try:
+        secrets = Settings().secrets
+    except Exception:
+        logger.warning("Feature request tools disabled: failed to load settings")
+        return
+
+    if not (
+        secrets.linear_api_key
+        and secrets.linear_feature_request_project_id
+        and secrets.linear_feature_request_team_id
+    ):
+        logger.info(
+            "Feature request tools disabled: LINEAR_API_KEY, "
+            "LINEAR_FEATURE_REQUEST_PROJECT_ID, or "
+            "LINEAR_FEATURE_REQUEST_TEAM_ID is not configured"
+        )
+        return
+
+    from .feature_requests import CreateFeatureRequestTool, SearchFeatureRequestsTool
+
+    TOOL_REGISTRY["search_feature_requests"] = SearchFeatureRequestsTool()
+    TOOL_REGISTRY["create_feature_request"] = CreateFeatureRequestTool()
+    logger.info("Feature request tools enabled")
+
+
+_register_feature_request_tools()
+
 # Export individual tool instances for backwards compatibility
 find_agent_tool = TOOL_REGISTRY["find_agent"]
 run_agent_tool = TOOL_REGISTRY["run_agent"]

autogpt_platform/backend/backend/api/features/chat/tools/feature_requests.py

@@ -0,0 +1,448 @@
+"""Feature request tools - search and create feature requests via Linear."""
+
+import logging
+from typing import Any
+
+from pydantic import SecretStr
+
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool
+from backend.api.features.chat.tools.models import (
+    ErrorResponse,
+    FeatureRequestCreatedResponse,
+    FeatureRequestInfo,
+    FeatureRequestSearchResponse,
+    NoResultsResponse,
+    ToolResponseBase,
+)
+from backend.blocks.linear._api import LinearClient
+from backend.data.model import APIKeyCredentials
+from backend.data.user import get_user_email_by_id
+from backend.util.settings import Settings
+
+logger = logging.getLogger(__name__)
+
+MAX_SEARCH_RESULTS = 10
+
+# GraphQL queries/mutations
+SEARCH_ISSUES_QUERY = """
+query SearchFeatureRequests($term: String!, $filter: IssueFilter, $first: Int) {
+  searchIssues(term: $term, filter: $filter, first: $first) {
+    nodes {
+      id
+      identifier
+      title
+      description
+    }
+  }
+}
+"""
+
+CUSTOMER_UPSERT_MUTATION = """
+mutation CustomerUpsert($input: CustomerUpsertInput!) {
+  customerUpsert(input: $input) {
+    success
+    customer {
+      id
+      name
+      externalIds
+    }
+  }
+}
+"""
+
+ISSUE_CREATE_MUTATION = """
+mutation IssueCreate($input: IssueCreateInput!) {
+  issueCreate(input: $input) {
+    success
+    issue {
+      id
+      identifier
+      title
+      url
+    }
+  }
+}
+"""
+
+CUSTOMER_NEED_CREATE_MUTATION = """
+mutation CustomerNeedCreate($input: CustomerNeedCreateInput!) {
+  customerNeedCreate(input: $input) {
+    success
+    need {
+      id
+      body
+      customer {
+        id
+        name
+      }
+      issue {
+        id
+        identifier
+        title
+        url
+      }
+    }
+  }
+}
+"""
+
+
+_settings: Settings | None = None
+
+
+def _get_settings() -> Settings:
+    global _settings
+    if _settings is None:
+        _settings = Settings()
+    return _settings
+
+
+def _get_linear_config() -> tuple[LinearClient, str, str]:
+    """Return a configured Linear client, project ID, and team ID.
+
+    Raises RuntimeError if any required setting is missing.
+    """
+    secrets = _get_settings().secrets
+    if not secrets.linear_api_key:
+        raise RuntimeError("LINEAR_API_KEY is not configured")
+    if not secrets.linear_feature_request_project_id:
+        raise RuntimeError("LINEAR_FEATURE_REQUEST_PROJECT_ID is not configured")
+    if not secrets.linear_feature_request_team_id:
+        raise RuntimeError("LINEAR_FEATURE_REQUEST_TEAM_ID is not configured")
+
+    credentials = APIKeyCredentials(
+        id="system-linear",
+        provider="linear",
+        api_key=SecretStr(secrets.linear_api_key),
+        title="System Linear API Key",
+    )
+    client = LinearClient(credentials=credentials)
+    return (
+        client,
+        secrets.linear_feature_request_project_id,
+        secrets.linear_feature_request_team_id,
+    )
+
+
+class SearchFeatureRequestsTool(BaseTool):
+    """Tool for searching existing feature requests in Linear."""
+
+    @property
+    def name(self) -> str:
+        return "search_feature_requests"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Search existing feature requests to check if a similar request "
+            "already exists before creating a new one. Returns matching feature "
+            "requests with their ID, title, and description."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Search term to find matching feature requests.",
+                },
+            },
+            "required": ["query"],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        query = kwargs.get("query", "").strip()
+        session_id = session.session_id if session else None
+
+        if not query:
+            return ErrorResponse(
+                message="Please provide a search query.",
+                error="Missing query parameter",
+                session_id=session_id,
+            )
+
+        try:
+            client, project_id, _team_id = _get_linear_config()
+            data = await client.query(
+                SEARCH_ISSUES_QUERY,
+                {
+                    "term": query,
+                    "filter": {
+                        "project": {"id": {"eq": project_id}},
+                    },
+                    "first": MAX_SEARCH_RESULTS,
+                },
+            )
+
+            nodes = data.get("searchIssues", {}).get("nodes", [])
+
+            if not nodes:
+                return NoResultsResponse(
+                    message=f"No feature requests found matching '{query}'.",
+                    suggestions=[
+                        "Try different keywords",
+                        "Use broader search terms",
+                        "You can create a new feature request if none exists",
+                    ],
+                    session_id=session_id,
+                )
+
+            results = [
+                FeatureRequestInfo(
+                    id=node["id"],
+                    identifier=node["identifier"],
+                    title=node["title"],
+                    description=node.get("description"),
+                )
+                for node in nodes
+            ]
+
+            return FeatureRequestSearchResponse(
+                message=f"Found {len(results)} feature request(s) matching '{query}'.",
+                results=results,
+                count=len(results),
+                query=query,
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.exception("Failed to search feature requests")
+            return ErrorResponse(
+                message="Failed to search feature requests.",
+                error=str(e),
+                session_id=session_id,
+            )
+
+
+class CreateFeatureRequestTool(BaseTool):
+    """Tool for creating feature requests (or adding needs to existing ones)."""
+
+    @property
+    def name(self) -> str:
+        return "create_feature_request"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Create a new feature request or add a customer need to an existing one. "
+            "Always search first with search_feature_requests to avoid duplicates. "
+            "If a matching request exists, pass its ID as existing_issue_id to add "
+            "the user's need to it instead of creating a duplicate."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "title": {
+                    "type": "string",
+                    "description": "Title for the feature request.",
+                },
+                "description": {
+                    "type": "string",
+                    "description": "Detailed description of what the user wants and why.",
+                },
+                "existing_issue_id": {
+                    "type": "string",
+                    "description": (
+                        "If adding a need to an existing feature request, "
+                        "provide its Linear issue ID (from search results). "
+                        "Omit to create a new feature request."
+                    ),
+                },
+            },
+            "required": ["title", "description"],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    async def _find_or_create_customer(
+        self, client: LinearClient, user_id: str, name: str
+    ) -> dict:
+        """Find existing customer by user_id or create a new one via upsert.
+
+        Args:
+            client: Linear API client.
+            user_id: Stable external ID used to deduplicate customers.
+            name: Human-readable display name (e.g. the user's email).
+        """
+        data = await client.mutate(
+            CUSTOMER_UPSERT_MUTATION,
+            {
+                "input": {
+                    "name": name,
+                    "externalId": user_id,
+                },
+            },
+        )
+        result = data.get("customerUpsert", {})
+        if not result.get("success"):
+            raise RuntimeError(f"Failed to upsert customer: {data}")
+        return result["customer"]
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        title = kwargs.get("title", "").strip()
+        description = kwargs.get("description", "").strip()
+        existing_issue_id = kwargs.get("existing_issue_id")
+        session_id = session.session_id if session else None
+
+        if not title or not description:
+            return ErrorResponse(
+                message="Both title and description are required.",
+                error="Missing required parameters",
+                session_id=session_id,
+            )
+
+        if not user_id:
+            return ErrorResponse(
+                message="Authentication required to create feature requests.",
+                error="Missing user_id",
+                session_id=session_id,
+            )
+
+        try:
+            client, project_id, team_id = _get_linear_config()
+        except Exception as e:
+            logger.exception("Failed to initialize Linear client")
+            return ErrorResponse(
+                message="Failed to create feature request.",
+                error=str(e),
+                session_id=session_id,
+            )
+
+        # Resolve a human-readable name (email) for the Linear customer record.
+        # Fall back to user_id if the lookup fails or returns None.
+        try:
+            customer_display_name = await get_user_email_by_id(user_id) or user_id
+        except Exception:
+            customer_display_name = user_id
+
+        # Step 1: Find or create customer for this user
+        try:
+            customer = await self._find_or_create_customer(
+                client, user_id, customer_display_name
+            )
+            customer_id = customer["id"]
+            customer_name = customer["name"]
+        except Exception as e:
+            logger.exception("Failed to upsert customer in Linear")
+            return ErrorResponse(
+                message="Failed to create feature request.",
+                error=str(e),
+                session_id=session_id,
+            )
+
+        # Step 2: Create or reuse issue
+        issue_id: str | None = None
+        issue_identifier: str | None = None
+        if existing_issue_id:
+            # Add need to existing issue - we still need the issue details for response
+            is_new_issue = False
+            issue_id = existing_issue_id
+        else:
+            # Create new issue in the feature requests project
+            try:
+                data = await client.mutate(
+                    ISSUE_CREATE_MUTATION,
+                    {
+                        "input": {
+                            "title": title,
+                            "description": description,
+                            "teamId": team_id,
+                            "projectId": project_id,
+                        },
+                    },
+                )
+                result = data.get("issueCreate", {})
+                if not result.get("success"):
+                    return ErrorResponse(
+                        message="Failed to create feature request issue.",
+                        error=str(data),
+                        session_id=session_id,
+                    )
+                issue = result["issue"]
+                issue_id = issue["id"]
+                issue_identifier = issue.get("identifier")
+            except Exception as e:
+                logger.exception("Failed to create feature request issue")
+                return ErrorResponse(
+                    message="Failed to create feature request.",
+                    error=str(e),
+                    session_id=session_id,
+                )
+            is_new_issue = True
+
+        # Step 3: Create customer need on the issue
+        try:
+            data = await client.mutate(
+                CUSTOMER_NEED_CREATE_MUTATION,
+                {
+                    "input": {
+                        "customerId": customer_id,
+                        "issueId": issue_id,
+                        "body": description,
+                        "priority": 0,
+                    },
+                },
+            )
+            need_result = data.get("customerNeedCreate", {})
+            if not need_result.get("success"):
+                orphaned = (
+                    {"issue_id": issue_id, "issue_identifier": issue_identifier}
+                    if is_new_issue
+                    else None
+                )
+                return ErrorResponse(
+                    message="Failed to attach customer need to the feature request.",
+                    error=str(data),
+                    details=orphaned,
+                    session_id=session_id,
+                )
+            need = need_result["need"]
+            issue_info = need["issue"]
+        except Exception as e:
+            logger.exception("Failed to create customer need")
+            orphaned = (
+                {"issue_id": issue_id, "issue_identifier": issue_identifier}
+                if is_new_issue
+                else None
+            )
+            return ErrorResponse(
+                message="Failed to attach customer need to the feature request.",
+                error=str(e),
+                details=orphaned,
+                session_id=session_id,
+            )
+
+        return FeatureRequestCreatedResponse(
+            message=(
+                f"{'Created new feature request' if is_new_issue else 'Added your request to existing feature request'}: "
+                f"{issue_info['title']}."
+            ),
+            issue_id=issue_info["id"],
+            issue_identifier=issue_info["identifier"],
+            issue_title=issue_info["title"],
+            issue_url=issue_info.get("url", ""),
+            is_new_issue=is_new_issue,
+            customer_name=customer_name,
+            session_id=session_id,
+        )

autogpt_platform/backend/backend/api/features/chat/tools/feature_requests_test.py

@@ -0,0 +1,615 @@
+"""Tests for SearchFeatureRequestsTool and CreateFeatureRequestTool."""
+
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from backend.api.features.chat.tools.feature_requests import (
+    CreateFeatureRequestTool,
+    SearchFeatureRequestsTool,
+)
+from backend.api.features.chat.tools.models import (
+    ErrorResponse,
+    FeatureRequestCreatedResponse,
+    FeatureRequestSearchResponse,
+    NoResultsResponse,
+)
+
+from ._test_data import make_session
+
+_TEST_USER_ID = "test-user-feature-requests"
+_TEST_USER_EMAIL = "testuser@example.com"
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+_FAKE_PROJECT_ID = "test-project-id"
+_FAKE_TEAM_ID = "test-team-id"
+
+
+def _mock_linear_config(*, query_return=None, mutate_return=None):
+    """Return a patched _get_linear_config that yields a mock LinearClient."""
+    client = AsyncMock()
+    if query_return is not None:
+        client.query.return_value = query_return
+    if mutate_return is not None:
+        client.mutate.return_value = mutate_return
+    return (
+        patch(
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
+            return_value=(client, _FAKE_PROJECT_ID, _FAKE_TEAM_ID),
+        ),
+        client,
+    )
+
+
+def _search_response(nodes: list[dict]) -> dict:
+    return {"searchIssues": {"nodes": nodes}}
+
+
+def _customer_upsert_response(
+    customer_id: str = "cust-1", name: str = _TEST_USER_EMAIL, success: bool = True
+) -> dict:
+    return {
+        "customerUpsert": {
+            "success": success,
+            "customer": {"id": customer_id, "name": name, "externalIds": [name]},
+        }
+    }
+
+
+def _issue_create_response(
+    issue_id: str = "issue-1",
+    identifier: str = "FR-1",
+    title: str = "New Feature",
+    success: bool = True,
+) -> dict:
+    return {
+        "issueCreate": {
+            "success": success,
+            "issue": {
+                "id": issue_id,
+                "identifier": identifier,
+                "title": title,
+                "url": f"https://linear.app/issue/{identifier}",
+            },
+        }
+    }
+
+
+def _need_create_response(
+    need_id: str = "need-1",
+    issue_id: str = "issue-1",
+    identifier: str = "FR-1",
+    title: str = "New Feature",
+    success: bool = True,
+) -> dict:
+    return {
+        "customerNeedCreate": {
+            "success": success,
+            "need": {
+                "id": need_id,
+                "body": "description",
+                "customer": {"id": "cust-1", "name": _TEST_USER_EMAIL},
+                "issue": {
+                    "id": issue_id,
+                    "identifier": identifier,
+                    "title": title,
+                    "url": f"https://linear.app/issue/{identifier}",
+                },
+            },
+        }
+    }
+
+
+# ===========================================================================
+# SearchFeatureRequestsTool
+# ===========================================================================
+
+
+class TestSearchFeatureRequestsTool:
+    """Tests for SearchFeatureRequestsTool._execute."""
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_successful_search(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        nodes = [
+            {
+                "id": "id-1",
+                "identifier": "FR-1",
+                "title": "Dark mode",
+                "description": "Add dark mode support",
+            },
+            {
+                "id": "id-2",
+                "identifier": "FR-2",
+                "title": "Dark theme",
+                "description": None,
+            },
+        ]
+        patcher, _ = _mock_linear_config(query_return=_search_response(nodes))
+        with patcher:
+            tool = SearchFeatureRequestsTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID, session=session, query="dark mode"
+            )
+
+        assert isinstance(resp, FeatureRequestSearchResponse)
+        assert resp.count == 2
+        assert resp.results[0].id == "id-1"
+        assert resp.results[1].identifier == "FR-2"
+        assert resp.query == "dark mode"
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_no_results(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, _ = _mock_linear_config(query_return=_search_response([]))
+        with patcher:
+            tool = SearchFeatureRequestsTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID, session=session, query="nonexistent"
+            )
+
+        assert isinstance(resp, NoResultsResponse)
+        assert "nonexistent" in resp.message
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_empty_query_returns_error(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        tool = SearchFeatureRequestsTool()
+        resp = await tool._execute(user_id=_TEST_USER_ID, session=session, query="   ")
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "query" in resp.error.lower()
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_missing_query_returns_error(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        tool = SearchFeatureRequestsTool()
+        resp = await tool._execute(user_id=_TEST_USER_ID, session=session)
+
+        assert isinstance(resp, ErrorResponse)
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_api_failure(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.query.side_effect = RuntimeError("Linear API down")
+        with patcher:
+            tool = SearchFeatureRequestsTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID, session=session, query="test"
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "Linear API down" in resp.error
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_malformed_node_returns_error(self):
+        """A node missing required keys should be caught by the try/except."""
+        session = make_session(user_id=_TEST_USER_ID)
+        # Node missing 'identifier' key
+        bad_nodes = [{"id": "id-1", "title": "Missing identifier"}]
+        patcher, _ = _mock_linear_config(query_return=_search_response(bad_nodes))
+        with patcher:
+            tool = SearchFeatureRequestsTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID, session=session, query="test"
+            )
+
+        assert isinstance(resp, ErrorResponse)
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_linear_client_init_failure(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        with patch(
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
+            side_effect=RuntimeError("No API key"),
+        ):
+            tool = SearchFeatureRequestsTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID, session=session, query="test"
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "No API key" in resp.error
+
+
+# ===========================================================================
+# CreateFeatureRequestTool
+# ===========================================================================
+
+
+class TestCreateFeatureRequestTool:
+    """Tests for CreateFeatureRequestTool._execute."""
+
+    @pytest.fixture(autouse=True)
+    def _patch_email_lookup(self):
+        with patch(
+            "backend.api.features.chat.tools.feature_requests.get_user_email_by_id",
+            new_callable=AsyncMock,
+            return_value=_TEST_USER_EMAIL,
+        ):
+            yield
+
+    # ---- Happy paths -------------------------------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_create_new_issue(self):
+        """Full happy path: upsert customer -> create issue -> attach need."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _issue_create_response(),
+            _need_create_response(),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="New Feature",
+                description="Please add this",
+            )
+
+        assert isinstance(resp, FeatureRequestCreatedResponse)
+        assert resp.is_new_issue is True
+        assert resp.issue_identifier == "FR-1"
+        assert resp.customer_name == _TEST_USER_EMAIL
+        assert client.mutate.call_count == 3
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_add_need_to_existing_issue(self):
+        """When existing_issue_id is provided, skip issue creation."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _need_create_response(issue_id="existing-1", identifier="FR-99"),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Existing Feature",
+                description="Me too",
+                existing_issue_id="existing-1",
+            )
+
+        assert isinstance(resp, FeatureRequestCreatedResponse)
+        assert resp.is_new_issue is False
+        assert resp.issue_id == "existing-1"
+        # Only 2 mutations: customer upsert + need create (no issue create)
+        assert client.mutate.call_count == 2
+
+    # ---- Validation errors -------------------------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_missing_title(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        tool = CreateFeatureRequestTool()
+        resp = await tool._execute(
+            user_id=_TEST_USER_ID,
+            session=session,
+            title="",
+            description="some desc",
+        )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "required" in resp.error.lower()
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_missing_description(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        tool = CreateFeatureRequestTool()
+        resp = await tool._execute(
+            user_id=_TEST_USER_ID,
+            session=session,
+            title="Some title",
+            description="",
+        )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "required" in resp.error.lower()
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_missing_user_id(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        tool = CreateFeatureRequestTool()
+        resp = await tool._execute(
+            user_id=None,
+            session=session,
+            title="Some title",
+            description="Some desc",
+        )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "user_id" in resp.error.lower()
+
+    # ---- Linear client init failure ----------------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_linear_client_init_failure(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        with patch(
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
+            side_effect=RuntimeError("No API key"),
+        ):
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "No API key" in resp.error
+
+    # ---- Customer upsert failures ------------------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_customer_upsert_api_error(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = RuntimeError("Customer API error")
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "Customer API error" in resp.error
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_customer_upsert_not_success(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.return_value = _customer_upsert_response(success=False)
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_customer_malformed_response(self):
+        """Customer dict missing 'id' key should be caught."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        # success=True but customer has no 'id'
+        client.mutate.return_value = {
+            "customerUpsert": {
+                "success": True,
+                "customer": {"name": _TEST_USER_ID},
+            }
+        }
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+
+    # ---- Issue creation failures -------------------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_issue_create_api_error(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            RuntimeError("Issue create failed"),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "Issue create failed" in resp.error
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_issue_create_not_success(self):
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _issue_create_response(success=False),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert "Failed to create feature request issue" in resp.message
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_issue_create_malformed_response(self):
+        """issueCreate success=True but missing 'issue' key."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            {"issueCreate": {"success": True}},  # no 'issue' key
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+
+    # ---- Customer need attachment failures ---------------------------------
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_need_create_api_error_new_issue(self):
+        """Need creation fails after new issue was created -> orphaned issue info."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _issue_create_response(issue_id="orphan-1", identifier="FR-10"),
+            RuntimeError("Need attach failed"),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.error is not None
+        assert "Need attach failed" in resp.error
+        assert resp.details is not None
+        assert resp.details["issue_id"] == "orphan-1"
+        assert resp.details["issue_identifier"] == "FR-10"
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_need_create_api_error_existing_issue(self):
+        """Need creation fails on existing issue -> no orphaned info."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            RuntimeError("Need attach failed"),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+                existing_issue_id="existing-1",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.details is None
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_need_create_not_success_includes_orphaned_info(self):
+        """customerNeedCreate returns success=False -> includes orphaned issue."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _issue_create_response(issue_id="orphan-2", identifier="FR-20"),
+            _need_create_response(success=False),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.details is not None
+        assert resp.details["issue_id"] == "orphan-2"
+        assert resp.details["issue_identifier"] == "FR-20"
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_need_create_not_success_existing_issue_no_details(self):
+        """customerNeedCreate fails on existing issue -> no orphaned info."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _need_create_response(success=False),
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+                existing_issue_id="existing-1",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.details is None
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_need_create_malformed_response(self):
+        """need_result missing 'need' key after success=True."""
+        session = make_session(user_id=_TEST_USER_ID)
+        patcher, client = _mock_linear_config()
+        client.mutate.side_effect = [
+            _customer_upsert_response(),
+            _issue_create_response(),
+            {"customerNeedCreate": {"success": True}},  # no 'need' key
+        ]
+
+        with patcher:
+            tool = CreateFeatureRequestTool()
+            resp = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                title="Title",
+                description="Desc",
+            )
+
+        assert isinstance(resp, ErrorResponse)
+        assert resp.details is not None
+        assert resp.details["issue_id"] == "issue-1"

autogpt_platform/backend/backend/api/features/chat/tools/models.py

@@ -41,6 +41,9 @@ class ResponseType(str, Enum):
     OPERATION_IN_PROGRESS = "operation_in_progress"
     # Input validation
     INPUT_VALIDATION_ERROR = "input_validation_error"
+    # Feature request types
+    FEATURE_REQUEST_SEARCH = "feature_request_search"
+    FEATURE_REQUEST_CREATED = "feature_request_created"
 
 
 # Base response model
@@ -430,3 +433,34 @@ class AsyncProcessingResponse(ToolResponseBase):
     status: str = "accepted"  # Must be "accepted" for detection
     operation_id: str | None = None
     task_id: str | None = None
+
+
+# Feature request models
+class FeatureRequestInfo(BaseModel):
+    """Information about a feature request issue."""
+
+    id: str
+    identifier: str
+    title: str
+    description: str | None = None
+
+
+class FeatureRequestSearchResponse(ToolResponseBase):
+    """Response for search_feature_requests tool."""
+
+    type: ResponseType = ResponseType.FEATURE_REQUEST_SEARCH
+    results: list[FeatureRequestInfo]
+    count: int
+    query: str
+
+
+class FeatureRequestCreatedResponse(ToolResponseBase):
+    """Response for create_feature_request tool."""
+
+    type: ResponseType = ResponseType.FEATURE_REQUEST_CREATED
+    issue_id: str
+    issue_identifier: str
+    issue_title: str
+    issue_url: str
+    is_new_issue: bool  # False if added to existing
+    customer_name: str

autogpt_platform/backend/backend/api/features/store/routes.py

@@ -393,7 +393,6 @@ async def get_creators(
 @router.get(
     "/creator/{username}",
     summary="Get creator details",
-    operation_id="getV2GetCreatorDetails",
     tags=["store", "public"],
     response_model=store_model.CreatorDetails,
 )

autogpt_platform/backend/backend/api/rest_api.py

@@ -18,7 +18,6 @@ from prisma.errors import PrismaError
 
 import backend.api.features.admin.credit_admin_routes
 import backend.api.features.admin.execution_analytics_routes
-import backend.api.features.admin.llm_routes
 import backend.api.features.admin.store_admin_routes
 import backend.api.features.builder
 import backend.api.features.builder.routes
@@ -39,15 +38,13 @@ import backend.data.db
 import backend.data.graph
 import backend.data.user
 import backend.integrations.webhooks.utils
-import backend.server.v2.llm.routes as public_llm_routes
 import backend.util.service
 import backend.util.settings
 from backend.api.features.chat.completion_consumer import (
     start_completion_consumer,
     stop_completion_consumer,
 )
-from backend.data import llm_registry
-from backend.data.block_cost_config import refresh_llm_costs
+from backend.blocks.llm import DEFAULT_LLM_MODEL
 from backend.data.model import Credentials
 from backend.integrations.providers import ProviderName
 from backend.monitoring.instrumentation import instrument_fastapi
@@ -118,27 +115,11 @@ async def lifespan_context(app: fastapi.FastAPI):
 
     AutoRegistry.patch_integrations()
 
-    # Refresh LLM registry before initializing blocks so blocks can use registry data
-    await llm_registry.refresh_llm_registry()
-    await refresh_llm_costs()
-
-    # Clear block schema caches so they're regenerated with updated discriminator_mapping
-    from backend.blocks._base import BlockSchema
-
-    BlockSchema.clear_all_schema_caches()
-
     await backend.data.block.initialize_blocks()
 
     await backend.data.user.migrate_and_encrypt_user_integrations()
     await backend.data.graph.fix_llm_provider_credentials()
-    # migrate_llm_models uses registry default model
-    from backend.blocks.llm import LlmModel
-
-    default_model_slug = llm_registry.get_default_model_slug()
-    if default_model_slug:
-        await backend.data.graph.migrate_llm_models(LlmModel(default_model_slug))
-    else:
-        logger.warning("Skipping LLM model migration: no default model available")
+    await backend.data.graph.migrate_llm_models(DEFAULT_LLM_MODEL)
     await backend.integrations.webhooks.utils.migrate_legacy_triggered_graphs()
 
     # Start chat completion consumer for Redis Streams notifications
@@ -340,16 +321,6 @@ app.include_router(
     tags=["v2", "executions", "review"],
     prefix="/api/review",
 )
-app.include_router(
-    backend.api.features.admin.llm_routes.router,
-    tags=["v2", "admin", "llm"],
-    prefix="/api/llm/admin",
-)
-app.include_router(
-    public_llm_routes.router,
-    tags=["v2", "llm"],
-    prefix="/api",
-)
 app.include_router(
     backend.api.features.library.routes.router, tags=["v2"], prefix="/api/library"
 )

autogpt_platform/backend/backend/api/ws_api.py

@@ -79,49 +79,11 @@ async def event_broadcaster(manager: ConnectionManager):
                     payload=notification.payload,
                 )
 
-        # Track registry pubsub for cleanup
-        registry_pubsub = None
-
-        async def registry_refresh_worker():
-            """Listen for LLM registry refresh notifications and broadcast to all clients."""
-            nonlocal registry_pubsub
-            from backend.data.llm_registry import REGISTRY_REFRESH_CHANNEL
-            from backend.data.redis_client import connect_async
-
-            redis = await connect_async()
-            registry_pubsub = redis.pubsub()
-            await registry_pubsub.subscribe(REGISTRY_REFRESH_CHANNEL)
-            logger.info(
-                "Subscribed to LLM registry refresh notifications for WebSocket broadcast"
-            )
-
-            async for message in registry_pubsub.listen():
-                if (
-                    message["type"] == "message"
-                    and message["channel"] == REGISTRY_REFRESH_CHANNEL
-                ):
-                    logger.info(
-                        "Broadcasting LLM registry refresh to all WebSocket clients"
-                    )
-                    await manager.broadcast_to_all(
-                        method=WSMethod.NOTIFICATION,
-                        data={
-                            "type": "LLM_REGISTRY_REFRESH",
-                            "event": "registry_updated",
-                        },
-                    )
-
-        await asyncio.gather(
-            execution_worker(),
-            notification_worker(),
-            registry_refresh_worker(),
-        )
+        await asyncio.gather(execution_worker(), notification_worker())
     finally:
         # Ensure PubSub connections are closed on any exit to prevent leaks
         await execution_bus.close()
         await notification_bus.close()
-        if registry_pubsub:
-            await registry_pubsub.close()
 
 
 async def authenticate_websocket(websocket: WebSocket) -> str:

autogpt_platform/backend/backend/blocks/_base.py

@@ -133,26 +133,7 @@ class BlockInfo(BaseModel):
 
 
 class BlockSchema(BaseModel):
-    cached_jsonschema: ClassVar[dict[str, Any] | None] = None
-
-    @classmethod
-    def clear_schema_cache(cls) -> None:
-        """Clear the cached JSON schema for this class."""
-        # Use None instead of {} because {} is truthy and would prevent regeneration
-        cls.cached_jsonschema = None  # type: ignore
-
-    @staticmethod
-    def clear_all_schema_caches() -> None:
-        """Clear cached JSON schemas for all BlockSchema subclasses."""
-
-        def clear_recursive(cls: type) -> None:
-            """Recursively clear cache for class and all subclasses."""
-            if hasattr(cls, "clear_schema_cache"):
-                cls.clear_schema_cache()
-            for subclass in cls.__subclasses__():
-                clear_recursive(subclass)
-
-        clear_recursive(BlockSchema)
+    cached_jsonschema: ClassVar[dict[str, Any]]
 
     @classmethod
     def jsonschema(cls) -> dict[str, Any]:
@@ -243,8 +224,7 @@ class BlockSchema(BaseModel):
         super().__pydantic_init_subclass__(**kwargs)
 
         # Reset cached JSON schema to prevent inheriting it from parent class
-        # Use None instead of {} because {} is truthy and would prevent regeneration
-        cls.cached_jsonschema = None
+        cls.cached_jsonschema = {}
 
         credentials_fields = cls.get_credentials_fields()
 

autogpt_platform/backend/backend/blocks/ai_condition.py

@@ -7,6 +7,7 @@ from backend.blocks._base import (
     BlockSchemaOutput,
 )
 from backend.blocks.llm import (
+    DEFAULT_LLM_MODEL,
     TEST_CREDENTIALS,
     TEST_CREDENTIALS_INPUT,
     AIBlockBase,
@@ -15,7 +16,6 @@ from backend.blocks.llm import (
     LlmModel,
     LLMResponse,
     llm_call,
-    llm_model_schema_extra,
 )
 from backend.data.model import APIKeyCredentials, NodeExecutionStats, SchemaField
 
@@ -50,10 +50,9 @@ class AIConditionBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for evaluating the condition.",
             advanced=False,
-            json_schema_extra=llm_model_schema_extra(),
         )
         credentials: AICredentials = AICredentialsField()
 
@@ -83,7 +82,7 @@ class AIConditionBlock(AIBlockBase):
                 "condition": "the input is an email address",
                 "yes_value": "Valid email",
                 "no_value": "Not an email",
-                "model": LlmModel.default(),
+                "model": DEFAULT_LLM_MODEL,
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_credentials=TEST_CREDENTIALS,

autogpt_platform/backend/backend/blocks/basic.py

@@ -126,6 +126,7 @@ class PrintToConsoleBlock(Block):
             output_schema=PrintToConsoleBlock.Output,
             test_input={"text": "Hello, World!"},
             is_sensitive_action=True,
+            disabled=True,  # Disabled per Nick Tindle's request (OPEN-3000)
             test_output=[
                 ("output", "Hello, World!"),
                 ("status", "printed"),

autogpt_platform/backend/backend/blocks/llm.py

@@ -4,18 +4,16 @@ import logging
 import re
 import secrets
 from abc import ABC
-from dataclasses import dataclass
-from enum import Enum
+from enum import Enum, EnumMeta
 from json import JSONDecodeError
-from typing import Any, Iterable, List, Literal, Optional
+from typing import Any, Iterable, List, Literal, NamedTuple, Optional
 
 import anthropic
 import ollama
 import openai
 from anthropic.types import ToolParam
 from groq import AsyncGroq
-from pydantic import BaseModel, GetCoreSchemaHandler, SecretStr
-from pydantic_core import CoreSchema, core_schema
+from pydantic import BaseModel, SecretStr
 
 from backend.blocks._base import (
     Block,
@@ -24,8 +22,6 @@ from backend.blocks._base import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data import llm_registry
-from backend.data.llm_registry import ModelMetadata
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -70,123 +66,114 @@ TEST_CREDENTIALS_INPUT = {
 
 
 def AICredentialsField() -> AICredentials:
-    """
-    Returns a CredentialsField for LLM providers.
-    The discriminator_mapping will be refreshed when the schema is generated
-    if it's empty, ensuring the LLM registry is loaded.
-    """
-    # Get the mapping now - it may be empty initially, but will be refreshed
-    # when the schema is generated via CredentialsMetaInput._add_json_schema_extra
-    mapping = llm_registry.get_llm_discriminator_mapping()
-
     return CredentialsField(
         description="API key for the LLM provider.",
         discriminator="model",
-        discriminator_mapping=mapping,  # May be empty initially, refreshed later
+        discriminator_mapping={
+            model.value: model.metadata.provider for model in LlmModel
+        },
     )
 
 
-def llm_model_schema_extra() -> dict[str, Any]:
-    return {"options": llm_registry.get_llm_model_schema_options()}
+class ModelMetadata(NamedTuple):
+    provider: str
+    context_window: int
+    max_output_tokens: int | None
+    display_name: str
+    provider_name: str
+    creator_name: str
+    price_tier: Literal[1, 2, 3]
 
 
-class LlmModelMeta(type):
-    """
-    Metaclass for LlmModel that enables attribute-style access to dynamic models.
-
-    This allows code like `LlmModel.GPT4O` to work by converting the attribute
-    name to a slug format:
-    - GPT4O -> gpt-4o
-    - GPT4O_MINI -> gpt-4o-mini
-    - CLAUDE_3_5_SONNET -> claude-3-5-sonnet
-    """
-
-    def __getattr__(cls, name: str):
-        # Don't intercept private/dunder attributes
-        if name.startswith("_"):
-            raise AttributeError(f"type object 'LlmModel' has no attribute '{name}'")
-
-        # Convert attribute name to slug format:
-        # 1. Lowercase: GPT4O -> gpt4o
-        # 2. Underscores to hyphens: GPT4O_MINI -> gpt4o-mini
-        slug = name.lower().replace("_", "-")
-
-        # Check for exact match in registry first (e.g., "o1" stays "o1")
-        registry_slugs = llm_registry.get_dynamic_model_slugs()
-        if slug in registry_slugs:
-            return cls(slug)
-
-        # If no exact match, try inserting hyphen between letter and digit
-        # e.g., gpt4o -> gpt-4o
-        transformed_slug = re.sub(r"([a-z])(\d)", r"\1-\2", slug)
-        return cls(transformed_slug)
-
-    def __iter__(cls):
-        """Iterate over all models from the registry.
-
-        Yields LlmModel instances for each model in the dynamic registry.
-        Used by __get_pydantic_json_schema__ to build model metadata.
-        """
-        for model in llm_registry.iter_dynamic_models():
-            yield cls(model.slug)
+class LlmModelMeta(EnumMeta):
+    pass
 
 
-class LlmModel(str, metaclass=LlmModelMeta):
-    """
-    Dynamic LLM model type that accepts any model slug from the registry.
-
-    This is a string subclass (not an Enum) that allows any model slug value.
-    All models are managed via the LLM Registry in the database.
-
-    Usage:
-        model = LlmModel("gpt-4o")  # Direct construction
-        model = LlmModel.GPT4O      # Attribute access (converted to "gpt-4o")
-        model.value                  # Returns the slug string
-        model.provider               # Returns the provider from registry
-    """
-
-    def __new__(cls, value: str):
-        if isinstance(value, LlmModel):
-            return value
-        return str.__new__(cls, value)
-
-    @classmethod
-    def __get_pydantic_core_schema__(
-        cls, source_type: Any, handler: GetCoreSchemaHandler
-    ) -> CoreSchema:
-        """
-        Tell Pydantic how to validate LlmModel.
-
-        Accepts strings and converts them to LlmModel instances.
-        """
-        return core_schema.no_info_after_validator_function(
-            cls,  # The validator function (LlmModel constructor)
-            core_schema.str_schema(),  # Accept string input
-            serialization=core_schema.to_string_ser_schema(),  # Serialize as string
-        )
-
-    @property
-    def value(self) -> str:
-        """Return the model slug (for compatibility with enum-style access)."""
-        return str(self)
-
-    @classmethod
-    def default(cls) -> "LlmModel":
-        """
-        Get the default model from the registry.
-
-        Returns the recommended model if set, otherwise gpt-4o if available
-        and enabled, otherwise the first enabled model from the registry.
-        Falls back to "gpt-4o" if registry is empty (e.g., at module import time).
-        """
-        from backend.data.llm_registry import get_default_model_slug
-
-        slug = get_default_model_slug()
-        if slug is None:
-            # Registry is empty (e.g., at module import time before DB connection).
-            # Fall back to gpt-4o for backward compatibility.
-            slug = "gpt-4o"
-        return cls(slug)
+class LlmModel(str, Enum, metaclass=LlmModelMeta):
+    # OpenAI models
+    O3_MINI = "o3-mini"
+    O3 = "o3-2025-04-16"
+    O1 = "o1"
+    O1_MINI = "o1-mini"
+    # GPT-5 models
+    GPT5_2 = "gpt-5.2-2025-12-11"
+    GPT5_1 = "gpt-5.1-2025-11-13"
+    GPT5 = "gpt-5-2025-08-07"
+    GPT5_MINI = "gpt-5-mini-2025-08-07"
+    GPT5_NANO = "gpt-5-nano-2025-08-07"
+    GPT5_CHAT = "gpt-5-chat-latest"
+    GPT41 = "gpt-4.1-2025-04-14"
+    GPT41_MINI = "gpt-4.1-mini-2025-04-14"
+    GPT4O_MINI = "gpt-4o-mini"
+    GPT4O = "gpt-4o"
+    GPT4_TURBO = "gpt-4-turbo"
+    GPT3_5_TURBO = "gpt-3.5-turbo"
+    # Anthropic models
+    CLAUDE_4_1_OPUS = "claude-opus-4-1-20250805"
+    CLAUDE_4_OPUS = "claude-opus-4-20250514"
+    CLAUDE_4_SONNET = "claude-sonnet-4-20250514"
+    CLAUDE_4_5_OPUS = "claude-opus-4-5-20251101"
+    CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
+    CLAUDE_4_5_HAIKU = "claude-haiku-4-5-20251001"
+    CLAUDE_4_6_OPUS = "claude-opus-4-6"
+    CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
+    # AI/ML API models
+    AIML_API_QWEN2_5_72B = "Qwen/Qwen2.5-72B-Instruct-Turbo"
+    AIML_API_LLAMA3_1_70B = "nvidia/llama-3.1-nemotron-70b-instruct"
+    AIML_API_LLAMA3_3_70B = "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+    AIML_API_META_LLAMA_3_1_70B = "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"
+    AIML_API_LLAMA_3_2_3B = "meta-llama/Llama-3.2-3B-Instruct-Turbo"
+    # Groq models
+    LLAMA3_3_70B = "llama-3.3-70b-versatile"
+    LLAMA3_1_8B = "llama-3.1-8b-instant"
+    # Ollama models
+    OLLAMA_LLAMA3_3 = "llama3.3"
+    OLLAMA_LLAMA3_2 = "llama3.2"
+    OLLAMA_LLAMA3_8B = "llama3"
+    OLLAMA_LLAMA3_405B = "llama3.1:405b"
+    OLLAMA_DOLPHIN = "dolphin-mistral:latest"
+    # OpenRouter models
+    OPENAI_GPT_OSS_120B = "openai/gpt-oss-120b"
+    OPENAI_GPT_OSS_20B = "openai/gpt-oss-20b"
+    GEMINI_2_5_PRO = "google/gemini-2.5-pro-preview-03-25"
+    GEMINI_3_PRO_PREVIEW = "google/gemini-3-pro-preview"
+    GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
+    GEMINI_2_0_FLASH = "google/gemini-2.0-flash-001"
+    GEMINI_2_5_FLASH_LITE_PREVIEW = "google/gemini-2.5-flash-lite-preview-06-17"
+    GEMINI_2_0_FLASH_LITE = "google/gemini-2.0-flash-lite-001"
+    MISTRAL_NEMO = "mistralai/mistral-nemo"
+    COHERE_COMMAND_R_08_2024 = "cohere/command-r-08-2024"
+    COHERE_COMMAND_R_PLUS_08_2024 = "cohere/command-r-plus-08-2024"
+    DEEPSEEK_CHAT = "deepseek/deepseek-chat"  # Actually: DeepSeek V3
+    DEEPSEEK_R1_0528 = "deepseek/deepseek-r1-0528"
+    PERPLEXITY_SONAR = "perplexity/sonar"
+    PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro"
+    PERPLEXITY_SONAR_DEEP_RESEARCH = "perplexity/sonar-deep-research"
+    NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = "nousresearch/hermes-3-llama-3.1-405b"
+    NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = "nousresearch/hermes-3-llama-3.1-70b"
+    AMAZON_NOVA_LITE_V1 = "amazon/nova-lite-v1"
+    AMAZON_NOVA_MICRO_V1 = "amazon/nova-micro-v1"
+    AMAZON_NOVA_PRO_V1 = "amazon/nova-pro-v1"
+    MICROSOFT_WIZARDLM_2_8X22B = "microsoft/wizardlm-2-8x22b"
+    GRYPHE_MYTHOMAX_L2_13B = "gryphe/mythomax-l2-13b"
+    META_LLAMA_4_SCOUT = "meta-llama/llama-4-scout"
+    META_LLAMA_4_MAVERICK = "meta-llama/llama-4-maverick"
+    GROK_4 = "x-ai/grok-4"
+    GROK_4_FAST = "x-ai/grok-4-fast"
+    GROK_4_1_FAST = "x-ai/grok-4.1-fast"
+    GROK_CODE_FAST_1 = "x-ai/grok-code-fast-1"
+    KIMI_K2 = "moonshotai/kimi-k2"
+    QWEN3_235B_A22B_THINKING = "qwen/qwen3-235b-a22b-thinking-2507"
+    QWEN3_CODER = "qwen/qwen3-coder"
+    # Llama API models
+    LLAMA_API_LLAMA_4_SCOUT = "Llama-4-Scout-17B-16E-Instruct-FP8"
+    LLAMA_API_LLAMA4_MAVERICK = "Llama-4-Maverick-17B-128E-Instruct-FP8"
+    LLAMA_API_LLAMA3_3_8B = "Llama-3.3-8B-Instruct"
+    LLAMA_API_LLAMA3_3_70B = "Llama-3.3-70B-Instruct"
+    # v0 by Vercel models
+    V0_1_5_MD = "v0-1.5-md"
+    V0_1_5_LG = "v0-1.5-lg"
+    V0_1_0_MD = "v0-1.0-md"
 
     @classmethod
     def __get_pydantic_json_schema__(cls, schema, handler):
@@ -194,15 +181,7 @@ class LlmModel(str, metaclass=LlmModelMeta):
         llm_model_metadata = {}
         for model in cls:
             model_name = model.value
-            # Skip disabled models - only show enabled models in the picker
-            if not llm_registry.is_model_enabled(model_name):
-                continue
-            # Use registry directly with None check to gracefully handle
-            # missing metadata during startup/import before registry is populated
-            metadata = llm_registry.get_llm_model_metadata(model_name)
-            if metadata is None:
-                # Skip models without metadata (registry not yet populated)
-                continue
+            metadata = model.metadata
             llm_model_metadata[model_name] = {
                 "creator": metadata.creator_name,
                 "creator_name": metadata.creator_name,
@@ -218,12 +197,7 @@ class LlmModel(str, metaclass=LlmModelMeta):
 
     @property
     def metadata(self) -> ModelMetadata:
-        metadata = llm_registry.get_llm_model_metadata(self.value)
-        if metadata:
-            return metadata
-        raise ValueError(
-            f"Missing metadata for model: {self.value}. Model not found in LLM registry."
-        )
+        return MODEL_METADATA[self]
 
     @property
     def provider(self) -> str:
@@ -238,125 +212,300 @@ class LlmModel(str, metaclass=LlmModelMeta):
         return self.metadata.max_output_tokens
 
 
-# Default model constant for backward compatibility
-# Uses the dynamic registry to get the default model
-DEFAULT_LLM_MODEL = LlmModel.default()
+MODEL_METADATA = {
+    # https://platform.openai.com/docs/models
+    LlmModel.O3: ModelMetadata("openai", 200000, 100000, "O3", "OpenAI", "OpenAI", 2),
+    LlmModel.O3_MINI: ModelMetadata(
+        "openai", 200000, 100000, "O3 Mini", "OpenAI", "OpenAI", 1
+    ),  # o3-mini-2025-01-31
+    LlmModel.O1: ModelMetadata(
+        "openai", 200000, 100000, "O1", "OpenAI", "OpenAI", 3
+    ),  # o1-2024-12-17
+    LlmModel.O1_MINI: ModelMetadata(
+        "openai", 128000, 65536, "O1 Mini", "OpenAI", "OpenAI", 2
+    ),  # o1-mini-2024-09-12
+    # GPT-5 models
+    LlmModel.GPT5_2: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5.2", "OpenAI", "OpenAI", 3
+    ),
+    LlmModel.GPT5_1: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5.1", "OpenAI", "OpenAI", 2
+    ),
+    LlmModel.GPT5: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_MINI: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5 Mini", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_NANO: ModelMetadata(
+        "openai", 400000, 128000, "GPT-5 Nano", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT5_CHAT: ModelMetadata(
+        "openai", 400000, 16384, "GPT-5 Chat Latest", "OpenAI", "OpenAI", 2
+    ),
+    LlmModel.GPT41: ModelMetadata(
+        "openai", 1047576, 32768, "GPT-4.1", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT41_MINI: ModelMetadata(
+        "openai", 1047576, 32768, "GPT-4.1 Mini", "OpenAI", "OpenAI", 1
+    ),
+    LlmModel.GPT4O_MINI: ModelMetadata(
+        "openai", 128000, 16384, "GPT-4o Mini", "OpenAI", "OpenAI", 1
+    ),  # gpt-4o-mini-2024-07-18
+    LlmModel.GPT4O: ModelMetadata(
+        "openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2
+    ),  # gpt-4o-2024-08-06
+    LlmModel.GPT4_TURBO: ModelMetadata(
+        "openai", 128000, 4096, "GPT-4 Turbo", "OpenAI", "OpenAI", 3
+    ),  # gpt-4-turbo-2024-04-09
+    LlmModel.GPT3_5_TURBO: ModelMetadata(
+        "openai", 16385, 4096, "GPT-3.5 Turbo", "OpenAI", "OpenAI", 1
+    ),  # gpt-3.5-turbo-0125
+    # https://docs.anthropic.com/en/docs/about-claude/models
+    LlmModel.CLAUDE_4_1_OPUS: ModelMetadata(
+        "anthropic", 200000, 32000, "Claude Opus 4.1", "Anthropic", "Anthropic", 3
+    ),  # claude-opus-4-1-20250805
+    LlmModel.CLAUDE_4_OPUS: ModelMetadata(
+        "anthropic", 200000, 32000, "Claude Opus 4", "Anthropic", "Anthropic", 3
+    ),  # claude-4-opus-20250514
+    LlmModel.CLAUDE_4_SONNET: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude Sonnet 4", "Anthropic", "Anthropic", 2
+    ),  # claude-4-sonnet-20250514
+    LlmModel.CLAUDE_4_6_OPUS: ModelMetadata(
+        "anthropic", 200000, 128000, "Claude Opus 4.6", "Anthropic", "Anthropic", 3
+    ),  # claude-opus-4-6
+    LlmModel.CLAUDE_4_5_OPUS: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude Opus 4.5", "Anthropic", "Anthropic", 3
+    ),  # claude-opus-4-5-20251101
+    LlmModel.CLAUDE_4_5_SONNET: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude Sonnet 4.5", "Anthropic", "Anthropic", 3
+    ),  # claude-sonnet-4-5-20250929
+    LlmModel.CLAUDE_4_5_HAIKU: ModelMetadata(
+        "anthropic", 200000, 64000, "Claude Haiku 4.5", "Anthropic", "Anthropic", 2
+    ),  # claude-haiku-4-5-20251001
+    LlmModel.CLAUDE_3_HAIKU: ModelMetadata(
+        "anthropic", 200000, 4096, "Claude 3 Haiku", "Anthropic", "Anthropic", 1
+    ),  # claude-3-haiku-20240307
+    # https://docs.aimlapi.com/api-overview/model-database/text-models
+    LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata(
+        "aiml_api", 32000, 8000, "Qwen 2.5 72B Instruct Turbo", "AI/ML", "Qwen", 1
+    ),
+    LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata(
+        "aiml_api",
+        128000,
+        40000,
+        "Llama 3.1 Nemotron 70B Instruct",
+        "AI/ML",
+        "Nvidia",
+        1,
+    ),
+    LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata(
+        "aiml_api", 128000, None, "Llama 3.3 70B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata(
+        "aiml_api", 131000, 2000, "Llama 3.1 70B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata(
+        "aiml_api", 128000, None, "Llama 3.2 3B Instruct Turbo", "AI/ML", "Meta", 1
+    ),
+    # https://console.groq.com/docs/models
+    LlmModel.LLAMA3_3_70B: ModelMetadata(
+        "groq", 128000, 32768, "Llama 3.3 70B Versatile", "Groq", "Meta", 1
+    ),
+    LlmModel.LLAMA3_1_8B: ModelMetadata(
+        "groq", 128000, 8192, "Llama 3.1 8B Instant", "Groq", "Meta", 1
+    ),
+    # https://ollama.com/library
+    LlmModel.OLLAMA_LLAMA3_3: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.3", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_2: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.2", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_8B: ModelMetadata(
+        "ollama", 8192, None, "Llama 3", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_LLAMA3_405B: ModelMetadata(
+        "ollama", 8192, None, "Llama 3.1 405B", "Ollama", "Meta", 1
+    ),
+    LlmModel.OLLAMA_DOLPHIN: ModelMetadata(
+        "ollama", 32768, None, "Dolphin Mistral Latest", "Ollama", "Mistral AI", 1
+    ),
+    # https://openrouter.ai/models
+    LlmModel.GEMINI_2_5_PRO: ModelMetadata(
+        "open_router",
+        1050000,
+        8192,
+        "Gemini 2.5 Pro Preview 03.25",
+        "OpenRouter",
+        "Google",
+        2,
+    ),
+    LlmModel.GEMINI_3_PRO_PREVIEW: ModelMetadata(
+        "open_router", 1048576, 65535, "Gemini 3 Pro Preview", "OpenRouter", "Google", 2
+    ),
+    LlmModel.GEMINI_2_5_FLASH: ModelMetadata(
+        "open_router", 1048576, 65535, "Gemini 2.5 Flash", "OpenRouter", "Google", 1
+    ),
+    LlmModel.GEMINI_2_0_FLASH: ModelMetadata(
+        "open_router", 1048576, 8192, "Gemini 2.0 Flash 001", "OpenRouter", "Google", 1
+    ),
+    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(
+        "open_router",
+        1048576,
+        65535,
+        "Gemini 2.5 Flash Lite Preview 06.17",
+        "OpenRouter",
+        "Google",
+        1,
+    ),
+    LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata(
+        "open_router",
+        1048576,
+        8192,
+        "Gemini 2.0 Flash Lite 001",
+        "OpenRouter",
+        "Google",
+        1,
+    ),
+    LlmModel.MISTRAL_NEMO: ModelMetadata(
+        "open_router", 128000, 4096, "Mistral Nemo", "OpenRouter", "Mistral AI", 1
+    ),
+    LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata(
+        "open_router", 128000, 4096, "Command R 08.2024", "OpenRouter", "Cohere", 1
+    ),
+    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata(
+        "open_router", 128000, 4096, "Command R Plus 08.2024", "OpenRouter", "Cohere", 2
+    ),
+    LlmModel.DEEPSEEK_CHAT: ModelMetadata(
+        "open_router", 64000, 2048, "DeepSeek Chat", "OpenRouter", "DeepSeek", 1
+    ),
+    LlmModel.DEEPSEEK_R1_0528: ModelMetadata(
+        "open_router", 163840, 163840, "DeepSeek R1 0528", "OpenRouter", "DeepSeek", 1
+    ),
+    LlmModel.PERPLEXITY_SONAR: ModelMetadata(
+        "open_router", 127000, 8000, "Sonar", "OpenRouter", "Perplexity", 1
+    ),
+    LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata(
+        "open_router", 200000, 8000, "Sonar Pro", "OpenRouter", "Perplexity", 2
+    ),
+    LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: ModelMetadata(
+        "open_router",
+        128000,
+        16000,
+        "Sonar Deep Research",
+        "OpenRouter",
+        "Perplexity",
+        3,
+    ),
+    LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B: ModelMetadata(
+        "open_router",
+        131000,
+        4096,
+        "Hermes 3 Llama 3.1 405B",
+        "OpenRouter",
+        "Nous Research",
+        1,
+    ),
+    LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B: ModelMetadata(
+        "open_router",
+        12288,
+        12288,
+        "Hermes 3 Llama 3.1 70B",
+        "OpenRouter",
+        "Nous Research",
+        1,
+    ),
+    LlmModel.OPENAI_GPT_OSS_120B: ModelMetadata(
+        "open_router", 131072, 131072, "GPT-OSS 120B", "OpenRouter", "OpenAI", 1
+    ),
+    LlmModel.OPENAI_GPT_OSS_20B: ModelMetadata(
+        "open_router", 131072, 32768, "GPT-OSS 20B", "OpenRouter", "OpenAI", 1
+    ),
+    LlmModel.AMAZON_NOVA_LITE_V1: ModelMetadata(
+        "open_router", 300000, 5120, "Nova Lite V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.AMAZON_NOVA_MICRO_V1: ModelMetadata(
+        "open_router", 128000, 5120, "Nova Micro V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata(
+        "open_router", 300000, 5120, "Nova Pro V1", "OpenRouter", "Amazon", 1
+    ),
+    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata(
+        "open_router", 65536, 4096, "WizardLM 2 8x22B", "OpenRouter", "Microsoft", 1
+    ),
+    LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata(
+        "open_router", 4096, 4096, "MythoMax L2 13B", "OpenRouter", "Gryphe", 1
+    ),
+    LlmModel.META_LLAMA_4_SCOUT: ModelMetadata(
+        "open_router", 131072, 131072, "Llama 4 Scout", "OpenRouter", "Meta", 1
+    ),
+    LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata(
+        "open_router", 1048576, 1000000, "Llama 4 Maverick", "OpenRouter", "Meta", 1
+    ),
+    LlmModel.GROK_4: ModelMetadata(
+        "open_router", 256000, 256000, "Grok 4", "OpenRouter", "xAI", 3
+    ),
+    LlmModel.GROK_4_FAST: ModelMetadata(
+        "open_router", 2000000, 30000, "Grok 4 Fast", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.GROK_4_1_FAST: ModelMetadata(
+        "open_router", 2000000, 30000, "Grok 4.1 Fast", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.GROK_CODE_FAST_1: ModelMetadata(
+        "open_router", 256000, 10000, "Grok Code Fast 1", "OpenRouter", "xAI", 1
+    ),
+    LlmModel.KIMI_K2: ModelMetadata(
+        "open_router", 131000, 131000, "Kimi K2", "OpenRouter", "Moonshot AI", 1
+    ),
+    LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata(
+        "open_router",
+        262144,
+        262144,
+        "Qwen 3 235B A22B Thinking 2507",
+        "OpenRouter",
+        "Qwen",
+        1,
+    ),
+    LlmModel.QWEN3_CODER: ModelMetadata(
+        "open_router", 262144, 262144, "Qwen 3 Coder", "OpenRouter", "Qwen", 3
+    ),
+    # Llama API models
+    LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata(
+        "llama_api",
+        128000,
+        4028,
+        "Llama 4 Scout 17B 16E Instruct FP8",
+        "Llama API",
+        "Meta",
+        1,
+    ),
+    LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata(
+        "llama_api",
+        128000,
+        4028,
+        "Llama 4 Maverick 17B 128E Instruct FP8",
+        "Llama API",
+        "Meta",
+        1,
+    ),
+    LlmModel.LLAMA_API_LLAMA3_3_8B: ModelMetadata(
+        "llama_api", 128000, 4028, "Llama 3.3 8B Instruct", "Llama API", "Meta", 1
+    ),
+    LlmModel.LLAMA_API_LLAMA3_3_70B: ModelMetadata(
+        "llama_api", 128000, 4028, "Llama 3.3 70B Instruct", "Llama API", "Meta", 1
+    ),
+    # v0 by Vercel models
+    LlmModel.V0_1_5_MD: ModelMetadata("v0", 128000, 64000, "v0 1.5 MD", "V0", "V0", 1),
+    LlmModel.V0_1_5_LG: ModelMetadata("v0", 512000, 64000, "v0 1.5 LG", "V0", "V0", 1),
+    LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000, "v0 1.0 MD", "V0", "V0", 1),
+}
 
+DEFAULT_LLM_MODEL = LlmModel.GPT5_2
 
-class ModelUnavailableError(ValueError):
-    """Raised when a requested LLM model cannot be resolved for use."""
-
-    pass
-
-
-@dataclass
-class ResolvedModel:
-    """Result of resolving a model for an LLM call."""
-
-    slug: str  # The actual model slug to use (may differ from requested if fallback)
-    provider: str
-    context_window: int
-    max_output_tokens: int
-    used_fallback: bool = False
-    original_slug: str | None = None  # Set if fallback was used
-
-
-async def resolve_model_for_call(llm_model: LlmModel) -> ResolvedModel:
-    """
-    Resolve a model for use in an LLM call.
-
-    Handles:
-    - Checking if the model exists in the registry
-    - Falling back to an enabled model from the same provider if disabled
-    - Refreshing the registry cache if model not found (with DB access)
-
-    Args:
-        llm_model: The requested LlmModel
-
-    Returns:
-        ResolvedModel with all necessary metadata for the call
-
-    Raises:
-        ModelUnavailableError: If model cannot be resolved (not found, disabled with no fallback)
-    """
-    from backend.data.llm_registry import (
-        get_fallback_model_for_disabled,
-        get_model_info,
-    )
-
-    model_info = get_model_info(llm_model.value)
-
-    # Case 1: Model found and disabled - try fallback
-    if model_info and not model_info.is_enabled:
-        fallback = get_fallback_model_for_disabled(llm_model.value)
-        if fallback:
-            logger.warning(
-                f"Model '{llm_model.value}' is disabled. Using fallback "
-                f"'{fallback.slug}' from same provider ({fallback.metadata.provider})."
-            )
-            return ResolvedModel(
-                slug=fallback.slug,
-                provider=fallback.metadata.provider,
-                context_window=fallback.metadata.context_window,
-                max_output_tokens=fallback.metadata.max_output_tokens or 2**15,
-                used_fallback=True,
-                original_slug=llm_model.value,
-            )
-        raise ModelUnavailableError(
-            f"Model '{llm_model.value}' is disabled and no fallback from the same "
-            f"provider is available. Enable the model or select a different one."
-        )
-
-    # Case 2: Model found and enabled - use it directly
-    if model_info:
-        return ResolvedModel(
-            slug=llm_model.value,
-            provider=model_info.metadata.provider,
-            context_window=model_info.metadata.context_window,
-            max_output_tokens=model_info.metadata.max_output_tokens or 2**15,
-        )
-
-    # Case 3: Model not in registry - try refresh if DB available
-    logger.warning(f"Model '{llm_model.value}' not found in registry cache")
-
-    from backend.data.db import is_connected
-
-    if not is_connected():
-        raise ModelUnavailableError(
-            f"Model '{llm_model.value}' not found in registry. "
-            f"The registry may need to be refreshed via the admin UI."
-        )
-
-    # Try refreshing the registry
-    try:
-        logger.info(f"Refreshing LLM registry for model '{llm_model.value}'")
-        await llm_registry.refresh_llm_registry()
-    except Exception as e:
-        raise ModelUnavailableError(
-            f"Model '{llm_model.value}' not found and registry refresh failed: {e}"
-        ) from e
-
-    # Check again after refresh
-    model_info = get_model_info(llm_model.value)
-    if not model_info:
-        raise ModelUnavailableError(
-            f"Model '{llm_model.value}' not found in registry. "
-            f"Add it via the admin UI at /admin/llms."
-        )
-
-    if not model_info.is_enabled:
-        raise ModelUnavailableError(
-            f"Model '{llm_model.value}' exists but is disabled. "
-            f"Enable it via the admin UI at /admin/llms."
-        )
-
-    logger.info(f"Model '{llm_model.value}' loaded after registry refresh")
-    return ResolvedModel(
-        slug=llm_model.value,
-        provider=model_info.metadata.provider,
-        context_window=model_info.metadata.context_window,
-        max_output_tokens=model_info.metadata.max_output_tokens or 2**15,
-    )
+for model in LlmModel:
+    if model not in MODEL_METADATA:
+        raise ValueError(f"Missing MODEL_METADATA metadata for model: {model}")
 
 
 class ToolCall(BaseModel):
@@ -382,12 +531,12 @@ class LLMResponse(BaseModel):
 
 def convert_openai_tool_fmt_to_anthropic(
     openai_tools: list[dict] | None = None,
-) -> Iterable[ToolParam] | anthropic.NotGiven:
+) -> Iterable[ToolParam] | anthropic.Omit:
     """
     Convert OpenAI tool format to Anthropic tool format.
     """
     if not openai_tools or len(openai_tools) == 0:
-        return anthropic.NOT_GIVEN
+        return anthropic.omit
 
     anthropic_tools = []
     for tool in openai_tools:
@@ -449,12 +598,7 @@ def get_parallel_tool_calls_param(
     llm_model: LlmModel, parallel_tool_calls: bool | None
 ) -> bool | openai.Omit:
     """Get the appropriate parallel_tool_calls parameter for OpenAI-compatible APIs."""
-    # Check for o-series models (o1, o1-mini, o3-mini, etc.) which don't support
-    # parallel tool calls. Handle both bare slugs ("o1-mini") and provider-prefixed
-    # slugs ("openai/o1-mini"). The pattern matches "o" followed by a digit at the
-    # start of the string or after a "/" separator.
-    is_o_series = re.search(r"(^|/)o\d", llm_model) is not None
-    if is_o_series or parallel_tool_calls is None:
+    if llm_model.startswith("o") or parallel_tool_calls is None:
         return openai.omit
     return parallel_tool_calls
 
@@ -490,22 +634,15 @@ async def llm_call(
             - prompt_tokens: The number of tokens used in the prompt.
             - completion_tokens: The number of tokens used in the completion.
     """
-    # Resolve the model - handles disabled models, fallbacks, and cache misses
-    resolved = await resolve_model_for_call(llm_model)
-
-    model_to_use = resolved.slug
-    provider = resolved.provider
-    context_window = resolved.context_window
-    model_max_output = resolved.max_output_tokens
-
-    # Create effective model for model-specific parameter resolution (e.g., o-series check)
-    effective_model = LlmModel(model_to_use)
+    provider = llm_model.metadata.provider
+    context_window = llm_model.context_window
 
     if compress_prompt_to_fit:
         result = await compress_context(
             messages=prompt,
-            target_tokens=context_window // 2,
+            target_tokens=llm_model.context_window // 2,
             client=None,  # Truncation-only, no LLM summarization
+            reserve=0,  # Caller handles response token budget separately
         )
         if result.error:
             logger.warning(
@@ -516,7 +653,7 @@ async def llm_call(
 
     # Calculate available tokens based on context window and input length
     estimated_input_tokens = estimate_token_count(prompt)
-    # model_max_output already set above
+    model_max_output = llm_model.max_output_tokens or int(2**15)
     user_max = max_tokens or model_max_output
     available_tokens = max(context_window - estimated_input_tokens, 0)
     max_tokens = max(min(available_tokens, model_max_output, user_max), 1)
@@ -527,14 +664,14 @@ async def llm_call(
         response_format = None
 
         parallel_tool_calls = get_parallel_tool_calls_param(
-            effective_model, parallel_tool_calls
+            llm_model, parallel_tool_calls
         )
 
         if force_json_output:
             response_format = {"type": "json_object"}
 
         response = await oai_client.chat.completions.create(
-            model=model_to_use,
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             response_format=response_format,  # type: ignore
             max_completion_tokens=max_tokens,
@@ -581,7 +718,7 @@ async def llm_call(
         )
         try:
             resp = await client.messages.create(
-                model=model_to_use,
+                model=llm_model.value,
                 system=sysprompt,
                 messages=messages,
                 max_tokens=max_tokens,
@@ -645,7 +782,7 @@ async def llm_call(
         client = AsyncGroq(api_key=credentials.api_key.get_secret_value())
         response_format = {"type": "json_object"} if force_json_output else None
         response = await client.chat.completions.create(
-            model=model_to_use,
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             response_format=response_format,  # type: ignore
             max_tokens=max_tokens,
@@ -667,7 +804,7 @@ async def llm_call(
         sys_messages = [p["content"] for p in prompt if p["role"] == "system"]
         usr_messages = [p["content"] for p in prompt if p["role"] != "system"]
         response = await client.generate(
-            model=model_to_use,
+            model=llm_model.value,
             prompt=f"{sys_messages}\n\n{usr_messages}",
             stream=False,
             options={"num_ctx": max_tokens},
@@ -689,7 +826,7 @@ async def llm_call(
         )
 
         parallel_tool_calls_param = get_parallel_tool_calls_param(
-            effective_model, parallel_tool_calls
+            llm_model, parallel_tool_calls
         )
 
         response = await client.chat.completions.create(
@@ -697,7 +834,7 @@ async def llm_call(
                 "HTTP-Referer": "https://agpt.co",
                 "X-Title": "AutoGPT",
             },
-            model=model_to_use,
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             max_tokens=max_tokens,
             tools=tools_param,  # type: ignore
@@ -731,7 +868,7 @@ async def llm_call(
         )
 
         parallel_tool_calls_param = get_parallel_tool_calls_param(
-            effective_model, parallel_tool_calls
+            llm_model, parallel_tool_calls
         )
 
         response = await client.chat.completions.create(
@@ -739,7 +876,7 @@ async def llm_call(
                 "HTTP-Referer": "https://agpt.co",
                 "X-Title": "AutoGPT",
             },
-            model=model_to_use,
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             max_tokens=max_tokens,
             tools=tools_param,  # type: ignore
@@ -766,7 +903,7 @@ async def llm_call(
             reasoning=reasoning,
         )
     elif provider == "aiml_api":
-        client = openai.AsyncOpenAI(
+        client = openai.OpenAI(
             base_url="https://api.aimlapi.com/v2",
             api_key=credentials.api_key.get_secret_value(),
             default_headers={
@@ -776,8 +913,8 @@ async def llm_call(
             },
         )
 
-        completion = await client.chat.completions.create(
-            model=model_to_use,
+        completion = client.chat.completions.create(
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             max_tokens=max_tokens,
         )
@@ -805,11 +942,11 @@ async def llm_call(
             response_format = {"type": "json_object"}
 
         parallel_tool_calls_param = get_parallel_tool_calls_param(
-            effective_model, parallel_tool_calls
+            llm_model, parallel_tool_calls
         )
 
         response = await client.chat.completions.create(
-            model=model_to_use,
+            model=llm_model.value,
             messages=prompt,  # type: ignore
             response_format=response_format,  # type: ignore
             max_tokens=max_tokens,
@@ -860,10 +997,9 @@ class AIStructuredResponseGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for answering the prompt.",
             advanced=False,
-            json_schema_extra=llm_model_schema_extra(),
         )
         force_json_output: bool = SchemaField(
             title="Restrict LLM to pure JSON output",
@@ -926,7 +1062,7 @@ class AIStructuredResponseGeneratorBlock(AIBlockBase):
             input_schema=AIStructuredResponseGeneratorBlock.Input,
             output_schema=AIStructuredResponseGeneratorBlock.Output,
             test_input={
-                "model": "gpt-4o",  # Using string value - enum accepts any model slug dynamically
+                "model": DEFAULT_LLM_MODEL,
                 "credentials": TEST_CREDENTIALS_INPUT,
                 "expected_format": {
                     "key1": "value1",
@@ -1292,10 +1428,9 @@ class AITextGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for answering the prompt.",
             advanced=False,
-            json_schema_extra=llm_model_schema_extra(),
         )
         credentials: AICredentials = AICredentialsField()
         sys_prompt: str = SchemaField(
@@ -1389,9 +1524,8 @@ class AITextSummarizerBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for summarizing the text.",
-            json_schema_extra=llm_model_schema_extra(),
         )
         focus: str = SchemaField(
             title="Focus",
@@ -1607,9 +1741,8 @@ class AIConversationBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for the conversation.",
-            json_schema_extra=llm_model_schema_extra(),
         )
         credentials: AICredentials = AICredentialsField()
         max_tokens: int | None = SchemaField(
@@ -1646,7 +1779,7 @@ class AIConversationBlock(AIBlockBase):
                     },
                     {"role": "user", "content": "Where was it played?"},
                 ],
-                "model": "gpt-4o",  # Using string value - enum accepts any model slug dynamically
+                "model": DEFAULT_LLM_MODEL,
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_credentials=TEST_CREDENTIALS,
@@ -1709,10 +1842,9 @@ class AIListGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=LlmModel.default,
+            default=DEFAULT_LLM_MODEL,
             description="The language model to use for generating the list.",
             advanced=True,
-            json_schema_extra=llm_model_schema_extra(),
         )
         credentials: AICredentials = AICredentialsField()
         max_retries: int = SchemaField(
@@ -1767,7 +1899,7 @@ class AIListGeneratorBlock(AIBlockBase):
                     "drawing explorers to uncover its mysteries. Each planet showcases the limitless possibilities of "
                     "fictional worlds."
                 ),
-                "model": "gpt-4o",  # Using string value - enum accepts any model slug dynamically
+                "model": DEFAULT_LLM_MODEL,
                 "credentials": TEST_CREDENTIALS_INPUT,
                 "max_retries": 3,
                 "force_json_output": False,

autogpt_platform/backend/backend/blocks/smart_decision_maker.py

@@ -226,10 +226,9 @@ class SmartDecisionMakerBlock(Block):
         )
         model: llm.LlmModel = SchemaField(
             title="LLM Model",
-            default_factory=llm.LlmModel.default,
+            default=llm.DEFAULT_LLM_MODEL,
             description="The language model to use for answering the prompt.",
             advanced=False,
-            json_schema_extra=llm.llm_model_schema_extra(),
         )
         credentials: llm.AICredentials = llm.AICredentialsField()
         multiple_tool_calls: bool = SchemaField(

autogpt_platform/backend/backend/blocks/stagehand/blocks.py

@@ -10,13 +10,13 @@ import stagehand.main
 from stagehand import Stagehand
 
 from backend.blocks.llm import (
+    MODEL_METADATA,
     AICredentials,
     AICredentialsField,
     LlmModel,
     ModelMetadata,
 )
 from backend.blocks.stagehand._config import stagehand as stagehand_provider
-from backend.data import llm_registry
 from backend.sdk import (
     APIKeyCredentials,
     Block,
@@ -91,7 +91,7 @@ class StagehandRecommendedLlmModel(str, Enum):
         Returns the provider name for the model in the required format for Stagehand:
         provider/model_name
         """
-        model_metadata = self.metadata
+        model_metadata = MODEL_METADATA[LlmModel(self.value)]
         model_name = self.value
 
         if len(model_name.split("/")) == 1 and not self.value.startswith(
@@ -102,28 +102,24 @@ class StagehandRecommendedLlmModel(str, Enum):
             ), "Logic failed and open_router provider attempted to be prepended to model name! in stagehand/_config.py"
             model_name = f"{model_metadata.provider}/{model_name}"
 
-        logger.debug(f"Model name: {model_name}")
+        logger.error(f"Model name: {model_name}")
         return model_name
 
     @property
     def provider(self) -> str:
-        return self.metadata.provider
+        return MODEL_METADATA[LlmModel(self.value)].provider
 
     @property
     def metadata(self) -> ModelMetadata:
-        metadata = llm_registry.get_llm_model_metadata(self.value)
-        if metadata:
-            return metadata
-        # Fallback to LlmModel enum if registry lookup fails
-        return LlmModel(self.value).metadata
+        return MODEL_METADATA[LlmModel(self.value)]
 
     @property
     def context_window(self) -> int:
-        return self.metadata.context_window
+        return MODEL_METADATA[LlmModel(self.value)].context_window
 
     @property
     def max_output_tokens(self) -> int | None:
-        return self.metadata.max_output_tokens
+        return MODEL_METADATA[LlmModel(self.value)].max_output_tokens
 
 
 class StagehandObserveBlock(Block):

autogpt_platform/backend/backend/data/block.py

@@ -19,30 +19,6 @@ CompletedBlockOutput = dict[str, list[Any]]  # Completed stream, collected as a
 
 
 async def initialize_blocks() -> None:
-    # Refresh LLM registry before initializing blocks so blocks can use registry data
-    # This ensures the registry cache is populated even in executor context
-    try:
-        from backend.data import llm_registry
-        from backend.data.block_cost_config import refresh_llm_costs
-
-        # Only refresh if we have DB access (check if Prisma is connected)
-        from backend.data.db import is_connected
-
-        if is_connected():
-            await llm_registry.refresh_llm_registry()
-            await refresh_llm_costs()
-            logger.info("LLM registry refreshed during block initialization")
-        else:
-            logger.warning(
-                "Prisma not connected, skipping LLM registry refresh during block initialization"
-            )
-    except Exception as exc:
-        logger.warning(
-            "Failed to refresh LLM registry during block initialization: %s", exc
-        )
-
-    # First, sync all provider costs to blocks
-    # Imported here to avoid circular import
     from backend.blocks import get_blocks
     from backend.sdk.cost_integration import sync_all_provider_costs
     from backend.util.retry import func_retry

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -1,8 +1,5 @@
-import logging
 from typing import Type
 
-import prisma.models
-
 from backend.blocks._base import Block, BlockCost, BlockCostType
 from backend.blocks.ai_image_customizer import AIImageCustomizerBlock, GeminiImageModel
 from backend.blocks.ai_image_generator_block import AIImageGeneratorBlock, ImageGenModel
@@ -27,11 +24,13 @@ from backend.blocks.ideogram import IdeogramModelBlock
 from backend.blocks.jina.embeddings import JinaEmbeddingBlock
 from backend.blocks.jina.search import ExtractWebsiteContentBlock, SearchTheWebBlock
 from backend.blocks.llm import (
+    MODEL_METADATA,
     AIConversationBlock,
     AIListGeneratorBlock,
     AIStructuredResponseGeneratorBlock,
     AITextGeneratorBlock,
     AITextSummarizerBlock,
+    LlmModel,
 )
 from backend.blocks.replicate.flux_advanced import ReplicateFluxAdvancedModelBlock
 from backend.blocks.replicate.replicate_block import ReplicateModelBlock
@@ -39,7 +38,6 @@ from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
 from backend.blocks.talking_head import CreateTalkingAvatarVideoBlock
 from backend.blocks.text_to_speech_block import UnrealTextToSpeechBlock
 from backend.blocks.video.narration import VideoNarrationBlock
-from backend.data import llm_registry
 from backend.integrations.credentials_store import (
     aiml_api_credentials,
     anthropic_credentials,
@@ -59,116 +57,210 @@ from backend.integrations.credentials_store import (
     v0_credentials,
 )
 
-logger = logging.getLogger(__name__)
+# =============== Configure the cost for each LLM Model call =============== #
 
-PROVIDER_CREDENTIALS = {
-    "openai": openai_credentials,
-    "anthropic": anthropic_credentials,
-    "groq": groq_credentials,
-    "open_router": open_router_credentials,
-    "llama_api": llama_api_credentials,
-    "aiml_api": aiml_api_credentials,
-    "v0": v0_credentials,
+MODEL_COST: dict[LlmModel, int] = {
+    LlmModel.O3: 4,
+    LlmModel.O3_MINI: 2,
+    LlmModel.O1: 16,
+    LlmModel.O1_MINI: 4,
+    # GPT-5 models
+    LlmModel.GPT5_2: 6,
+    LlmModel.GPT5_1: 5,
+    LlmModel.GPT5: 2,
+    LlmModel.GPT5_MINI: 1,
+    LlmModel.GPT5_NANO: 1,
+    LlmModel.GPT5_CHAT: 5,
+    LlmModel.GPT41: 2,
+    LlmModel.GPT41_MINI: 1,
+    LlmModel.GPT4O_MINI: 1,
+    LlmModel.GPT4O: 3,
+    LlmModel.GPT4_TURBO: 10,
+    LlmModel.GPT3_5_TURBO: 1,
+    LlmModel.CLAUDE_4_1_OPUS: 21,
+    LlmModel.CLAUDE_4_OPUS: 21,
+    LlmModel.CLAUDE_4_SONNET: 5,
+    LlmModel.CLAUDE_4_6_OPUS: 14,
+    LlmModel.CLAUDE_4_5_HAIKU: 4,
+    LlmModel.CLAUDE_4_5_OPUS: 14,
+    LlmModel.CLAUDE_4_5_SONNET: 9,
+    LlmModel.CLAUDE_3_HAIKU: 1,
+    LlmModel.AIML_API_QWEN2_5_72B: 1,
+    LlmModel.AIML_API_LLAMA3_1_70B: 1,
+    LlmModel.AIML_API_LLAMA3_3_70B: 1,
+    LlmModel.AIML_API_META_LLAMA_3_1_70B: 1,
+    LlmModel.AIML_API_LLAMA_3_2_3B: 1,
+    LlmModel.LLAMA3_3_70B: 1,
+    LlmModel.LLAMA3_1_8B: 1,
+    LlmModel.OLLAMA_LLAMA3_3: 1,
+    LlmModel.OLLAMA_LLAMA3_2: 1,
+    LlmModel.OLLAMA_LLAMA3_8B: 1,
+    LlmModel.OLLAMA_LLAMA3_405B: 1,
+    LlmModel.OLLAMA_DOLPHIN: 1,
+    LlmModel.OPENAI_GPT_OSS_120B: 1,
+    LlmModel.OPENAI_GPT_OSS_20B: 1,
+    LlmModel.GEMINI_2_5_PRO: 4,
+    LlmModel.GEMINI_3_PRO_PREVIEW: 5,
+    LlmModel.GEMINI_2_5_FLASH: 1,
+    LlmModel.GEMINI_2_0_FLASH: 1,
+    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
+    LlmModel.GEMINI_2_0_FLASH_LITE: 1,
+    LlmModel.MISTRAL_NEMO: 1,
+    LlmModel.COHERE_COMMAND_R_08_2024: 1,
+    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: 3,
+    LlmModel.DEEPSEEK_CHAT: 2,
+    LlmModel.DEEPSEEK_R1_0528: 1,
+    LlmModel.PERPLEXITY_SONAR: 1,
+    LlmModel.PERPLEXITY_SONAR_PRO: 5,
+    LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: 10,
+    LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B: 1,
+    LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B: 1,
+    LlmModel.AMAZON_NOVA_LITE_V1: 1,
+    LlmModel.AMAZON_NOVA_MICRO_V1: 1,
+    LlmModel.AMAZON_NOVA_PRO_V1: 1,
+    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: 1,
+    LlmModel.GRYPHE_MYTHOMAX_L2_13B: 1,
+    LlmModel.META_LLAMA_4_SCOUT: 1,
+    LlmModel.META_LLAMA_4_MAVERICK: 1,
+    LlmModel.LLAMA_API_LLAMA_4_SCOUT: 1,
+    LlmModel.LLAMA_API_LLAMA4_MAVERICK: 1,
+    LlmModel.LLAMA_API_LLAMA3_3_8B: 1,
+    LlmModel.LLAMA_API_LLAMA3_3_70B: 1,
+    LlmModel.GROK_4: 9,
+    LlmModel.GROK_4_FAST: 1,
+    LlmModel.GROK_4_1_FAST: 1,
+    LlmModel.GROK_CODE_FAST_1: 1,
+    LlmModel.KIMI_K2: 1,
+    LlmModel.QWEN3_235B_A22B_THINKING: 1,
+    LlmModel.QWEN3_CODER: 9,
+    # v0 by Vercel models
+    LlmModel.V0_1_5_MD: 1,
+    LlmModel.V0_1_5_LG: 2,
+    LlmModel.V0_1_0_MD: 1,
 }
 
-# =============== Configure the cost for each LLM Model call =============== #
-# All LLM costs now come from the database via llm_registry
-
-LLM_COST: list[BlockCost] = []
+for model in LlmModel:
+    if model not in MODEL_COST:
+        raise ValueError(f"Missing MODEL_COST for model: {model}")
 
 
-async def _build_llm_costs_from_registry() -> list[BlockCost]:
-    """
-    Build BlockCost list from all models in the LLM registry.
-
-    This function checks for active model migrations with customCreditCost overrides.
-    When a model has been migrated with a custom price, that price is used instead
-    of the target model's default cost.
-    """
-    # Query active migrations with custom pricing overrides.
-    # Note: LlmModelMigration is system-level data (no userId field) and this function
-    # is only called during app startup and admin operations, so no user ID filter needed.
-    migration_overrides: dict[str, int] = {}
-    try:
-        active_migrations = await prisma.models.LlmModelMigration.prisma().find_many(
-            where={
-                "isReverted": False,
-                "customCreditCost": {"not": None},
-            }
-        )
-        # Key by targetModelSlug since that's the model nodes are now using
-        # after migration. The custom cost applies to the target model.
-        migration_overrides = {
-            migration.targetModelSlug: migration.customCreditCost
-            for migration in active_migrations
-            if migration.customCreditCost is not None
-        }
-        if migration_overrides:
-            logger.info(
-                "Found %d active model migrations with custom pricing overrides",
-                len(migration_overrides),
-            )
-    except Exception as exc:
-        logger.warning(
-            "Failed to query model migration overrides: %s. Proceeding with default costs.",
-            exc,
-            exc_info=True,
-        )
-
-    costs: list[BlockCost] = []
-    for model in llm_registry.iter_dynamic_models():
-        for cost in model.costs:
-            credentials = PROVIDER_CREDENTIALS.get(cost.credential_provider)
-            if not credentials:
-                logger.warning(
-                    "Skipping cost entry for %s due to unknown credentials provider %s",
-                    model.slug,
-                    cost.credential_provider,
-                )
-                continue
-
-            # Check if this model has a custom cost override from migration
-            cost_amount = migration_overrides.get(model.slug, cost.credit_cost)
-
-            if model.slug in migration_overrides:
-                logger.debug(
-                    "Applying custom cost override for model %s: %d credits (default: %d)",
-                    model.slug,
-                    cost_amount,
-                    cost.credit_cost,
-                )
-
-            cost_filter = {
-                "model": model.slug,
+LLM_COST = (
+    # Anthropic Models
+    [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
                 "credentials": {
-                    "id": credentials.id,
-                    "provider": credentials.provider,
-                    "type": credentials.type,
+                    "id": anthropic_credentials.id,
+                    "provider": anthropic_credentials.provider,
+                    "type": anthropic_credentials.type,
                 },
-            }
-            costs.append(
-                BlockCost(
-                    cost_type=BlockCostType.RUN,
-                    cost_filter=cost_filter,
-                    cost_amount=cost_amount,
-                )
-            )
-    return costs
-
-
-async def refresh_llm_costs() -> None:
-    """
-    Refresh LLM costs from the registry. All costs now come from the database.
-
-    This function also checks for active model migrations with custom pricing overrides
-    and applies them to ensure accurate billing.
-    """
-    LLM_COST.clear()
-    LLM_COST.extend(await _build_llm_costs_from_registry())
-
-
-# Initial load will happen after registry is refreshed at startup
-# Don't call refresh_llm_costs() here - it will be called after registry refresh
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "anthropic"
+    ]
+    # OpenAI Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {
+                    "id": openai_credentials.id,
+                    "provider": openai_credentials.provider,
+                    "type": openai_credentials.type,
+                },
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "openai"
+    ]
+    # Groq Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {"id": groq_credentials.id},
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "groq"
+    ]
+    # Open Router Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {
+                    "id": open_router_credentials.id,
+                    "provider": open_router_credentials.provider,
+                    "type": open_router_credentials.type,
+                },
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "open_router"
+    ]
+    # Llama API Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {
+                    "id": llama_api_credentials.id,
+                    "provider": llama_api_credentials.provider,
+                    "type": llama_api_credentials.type,
+                },
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "llama_api"
+    ]
+    # v0 by Vercel Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {
+                    "id": v0_credentials.id,
+                    "provider": v0_credentials.provider,
+                    "type": v0_credentials.type,
+                },
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "v0"
+    ]
+    # AI/ML Api Models
+    + [
+        BlockCost(
+            cost_type=BlockCostType.RUN,
+            cost_filter={
+                "model": model,
+                "credentials": {
+                    "id": aiml_api_credentials.id,
+                    "provider": aiml_api_credentials.provider,
+                    "type": aiml_api_credentials.type,
+                },
+            },
+            cost_amount=cost,
+        )
+        for model, cost in MODEL_COST.items()
+        if MODEL_METADATA[model].provider == "aiml_api"
+    ]
+)
 
 # =============== This is the exhaustive list of cost for each Block =============== #
 

autogpt_platform/backend/backend/data/graph.py

@@ -1625,10 +1625,8 @@ async def migrate_llm_models(migrate_to: LlmModel):
             if field.annotation == LlmModel:
                 llm_model_fields[block.id] = field_name
 
-    # Get all model slugs from the registry (dynamic, not hardcoded enum)
-    from backend.data import llm_registry
-
-    enum_values = list(llm_registry.get_all_model_slugs_for_validation())
+    # Convert enum values to a list of strings for the SQL query
+    enum_values = [v.value for v in LlmModel]
     escaped_enum_values = repr(tuple(enum_values))  # hack but works
 
     # Update each block

autogpt_platform/backend/backend/data/llm_registry/__init__.py

@@ -1,72 +0,0 @@
-"""
-LLM Registry module for managing LLM models, providers, and costs dynamically.
-
-This module provides a database-driven registry system for LLM models,
-replacing hardcoded model configurations with a flexible admin-managed system.
-"""
-
-from backend.data.llm_registry.model import ModelMetadata
-
-# Re-export for backwards compatibility
-from backend.data.llm_registry.notifications import (
-    REGISTRY_REFRESH_CHANNEL,
-    publish_registry_refresh_notification,
-    subscribe_to_registry_refresh,
-)
-from backend.data.llm_registry.registry import (
-    RegistryModel,
-    RegistryModelCost,
-    RegistryModelCreator,
-    get_all_model_slugs_for_validation,
-    get_default_model_slug,
-    get_dynamic_model_slugs,
-    get_fallback_model_for_disabled,
-    get_llm_discriminator_mapping,
-    get_llm_model_cost,
-    get_llm_model_metadata,
-    get_llm_model_schema_options,
-    get_model_info,
-    is_model_enabled,
-    iter_dynamic_models,
-    refresh_llm_registry,
-    register_static_costs,
-    register_static_metadata,
-)
-from backend.data.llm_registry.schema_utils import (
-    is_llm_model_field,
-    refresh_llm_discriminator_mapping,
-    refresh_llm_model_options,
-    update_schema_with_llm_registry,
-)
-
-__all__ = [
-    # Types
-    "ModelMetadata",
-    "RegistryModel",
-    "RegistryModelCost",
-    "RegistryModelCreator",
-    # Registry functions
-    "get_all_model_slugs_for_validation",
-    "get_default_model_slug",
-    "get_dynamic_model_slugs",
-    "get_fallback_model_for_disabled",
-    "get_llm_discriminator_mapping",
-    "get_llm_model_cost",
-    "get_llm_model_metadata",
-    "get_llm_model_schema_options",
-    "get_model_info",
-    "is_model_enabled",
-    "iter_dynamic_models",
-    "refresh_llm_registry",
-    "register_static_costs",
-    "register_static_metadata",
-    # Notifications
-    "REGISTRY_REFRESH_CHANNEL",
-    "publish_registry_refresh_notification",
-    "subscribe_to_registry_refresh",
-    # Schema utilities
-    "is_llm_model_field",
-    "refresh_llm_discriminator_mapping",
-    "refresh_llm_model_options",
-    "update_schema_with_llm_registry",
-]

autogpt_platform/backend/backend/data/llm_registry/model.py

@@ -1,25 +0,0 @@
-"""Type definitions for LLM model metadata."""
-
-from typing import Literal, NamedTuple
-
-
-class ModelMetadata(NamedTuple):
-    """Metadata for an LLM model.
-
-    Attributes:
-        provider: The provider identifier (e.g., "openai", "anthropic")
-        context_window: Maximum context window size in tokens
-        max_output_tokens: Maximum output tokens (None if unlimited)
-        display_name: Human-readable name for the model
-        provider_name: Human-readable provider name (e.g., "OpenAI", "Anthropic")
-        creator_name: Name of the organization that created the model
-        price_tier: Relative cost tier (1=cheapest, 2=medium, 3=expensive)
-    """
-
-    provider: str
-    context_window: int
-    max_output_tokens: int | None
-    display_name: str
-    provider_name: str
-    creator_name: str
-    price_tier: Literal[1, 2, 3]

autogpt_platform/backend/backend/data/llm_registry/notifications.py

@@ -1,89 +0,0 @@
-"""
-Redis pub/sub notifications for LLM registry updates.
-
-When models are added/updated/removed via the admin UI, this module
-publishes notifications to Redis that all executor services subscribe to,
-ensuring they refresh their registry cache in real-time.
-"""
-
-import asyncio
-import logging
-from typing import Any
-
-from backend.data.redis_client import connect_async
-
-logger = logging.getLogger(__name__)
-
-# Redis channel name for LLM registry refresh notifications
-REGISTRY_REFRESH_CHANNEL = "llm_registry:refresh"
-
-
-async def publish_registry_refresh_notification() -> None:
-    """
-    Publish a notification to Redis that the LLM registry has been updated.
-    All executor services subscribed to this channel will refresh their registry.
-    """
-    try:
-        redis = await connect_async()
-        await redis.publish(REGISTRY_REFRESH_CHANNEL, "refresh")
-        logger.info("Published LLM registry refresh notification to Redis")
-    except Exception as exc:
-        logger.warning(
-            "Failed to publish LLM registry refresh notification: %s",
-            exc,
-            exc_info=True,
-        )
-
-
-async def subscribe_to_registry_refresh(
-    on_refresh: Any,  # Async callable that takes no args
-) -> None:
-    """
-    Subscribe to Redis notifications for LLM registry updates.
-    This runs in a loop and processes messages as they arrive.
-
-    Args:
-        on_refresh: Async callable to execute when a refresh notification is received
-    """
-    try:
-        redis = await connect_async()
-        pubsub = redis.pubsub()
-        await pubsub.subscribe(REGISTRY_REFRESH_CHANNEL)
-        logger.info(
-            "Subscribed to LLM registry refresh notifications on channel: %s",
-            REGISTRY_REFRESH_CHANNEL,
-        )
-
-        # Process messages in a loop
-        while True:
-            try:
-                message = await pubsub.get_message(
-                    ignore_subscribe_messages=True, timeout=1.0
-                )
-                if (
-                    message
-                    and message["type"] == "message"
-                    and message["channel"] == REGISTRY_REFRESH_CHANNEL
-                ):
-                    logger.info("Received LLM registry refresh notification")
-                    try:
-                        await on_refresh()
-                    except Exception as exc:
-                        logger.error(
-                            "Error refreshing LLM registry from notification: %s",
-                            exc,
-                            exc_info=True,
-                        )
-            except Exception as exc:
-                logger.warning(
-                    "Error processing registry refresh message: %s", exc, exc_info=True
-                )
-                # Continue listening even if one message fails
-                await asyncio.sleep(1)
-    except Exception as exc:
-        logger.error(
-            "Failed to subscribe to LLM registry refresh notifications: %s",
-            exc,
-            exc_info=True,
-        )
-        raise

autogpt_platform/backend/backend/data/llm_registry/registry.py

@@ -1,388 +0,0 @@
-"""Core LLM registry implementation for managing models dynamically."""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-from dataclasses import dataclass, field
-from typing import Any, Iterable
-
-import prisma.models
-
-from backend.data.llm_registry.model import ModelMetadata
-
-logger = logging.getLogger(__name__)
-
-
-def _json_to_dict(value: Any) -> dict[str, Any]:
-    """Convert Prisma Json type to dict, with fallback to empty dict."""
-    if value is None:
-        return {}
-    if isinstance(value, dict):
-        return value
-    # Prisma Json type should always be a dict at runtime
-    return dict(value) if value else {}
-
-
-@dataclass(frozen=True)
-class RegistryModelCost:
-    """Cost configuration for an LLM model."""
-
-    credit_cost: int
-    credential_provider: str
-    credential_id: str | None
-    credential_type: str | None
-    currency: str | None
-    metadata: dict[str, Any]
-
-
-@dataclass(frozen=True)
-class RegistryModelCreator:
-    """Creator information for an LLM model."""
-
-    id: str
-    name: str
-    display_name: str
-    description: str | None
-    website_url: str | None
-    logo_url: str | None
-
-
-@dataclass(frozen=True)
-class RegistryModel:
-    """Represents a model in the LLM registry."""
-
-    slug: str
-    display_name: str
-    description: str | None
-    metadata: ModelMetadata
-    capabilities: dict[str, Any]
-    extra_metadata: dict[str, Any]
-    provider_display_name: str
-    is_enabled: bool
-    is_recommended: bool = False
-    costs: tuple[RegistryModelCost, ...] = field(default_factory=tuple)
-    creator: RegistryModelCreator | None = None
-
-
-_static_metadata: dict[str, ModelMetadata] = {}
-_static_costs: dict[str, int] = {}
-_dynamic_models: dict[str, RegistryModel] = {}
-_schema_options: list[dict[str, str]] = []
-_discriminator_mapping: dict[str, str] = {}
-_lock = asyncio.Lock()
-
-
-def register_static_metadata(metadata: dict[Any, ModelMetadata]) -> None:
-    """Register static metadata for legacy models (deprecated)."""
-    _static_metadata.update({str(key): value for key, value in metadata.items()})
-    _refresh_cached_schema()
-
-
-def register_static_costs(costs: dict[Any, int]) -> None:
-    """Register static costs for legacy models (deprecated)."""
-    _static_costs.update({str(key): value for key, value in costs.items()})
-
-
-def _build_schema_options() -> list[dict[str, str]]:
-    """Build schema options for model selection dropdown. Only includes enabled models."""
-    options: list[dict[str, str]] = []
-    # Only include enabled models in the dropdown options
-    for model in sorted(_dynamic_models.values(), key=lambda m: m.display_name.lower()):
-        if model.is_enabled:
-            options.append(
-                {
-                    "label": model.display_name,
-                    "value": model.slug,
-                    "group": model.metadata.provider,
-                    "description": model.description or "",
-                }
-            )
-
-    for slug, metadata in _static_metadata.items():
-        if slug in _dynamic_models:
-            continue
-        options.append(
-            {
-                "label": slug,
-                "value": slug,
-                "group": metadata.provider,
-                "description": "",
-            }
-        )
-    return options
-
-
-async def refresh_llm_registry() -> None:
-    """Refresh the LLM registry from the database. Loads all models (enabled and disabled)."""
-    async with _lock:
-        try:
-            records = await prisma.models.LlmModel.prisma().find_many(
-                include={
-                    "Provider": True,
-                    "Costs": True,
-                    "Creator": True,
-                }
-            )
-            logger.debug("Found %d LLM model records in database", len(records))
-        except Exception as exc:
-            logger.error(
-                "Failed to refresh LLM registry from DB: %s", exc, exc_info=True
-            )
-            return
-
-        dynamic: dict[str, RegistryModel] = {}
-        for record in records:
-            provider_name = (
-                record.Provider.name if record.Provider else record.providerId
-            )
-            provider_display_name = (
-                record.Provider.displayName if record.Provider else record.providerId
-            )
-            # Creator name: prefer Creator.name, fallback to provider display name
-            creator_name = (
-                record.Creator.name if record.Creator else provider_display_name
-            )
-            # Price tier: default to 1 (cheapest) if not set
-            price_tier = getattr(record, "priceTier", 1) or 1
-            # Clamp to valid range 1-3
-            price_tier = max(1, min(3, price_tier))
-
-            metadata = ModelMetadata(
-                provider=provider_name,
-                context_window=record.contextWindow,
-                max_output_tokens=record.maxOutputTokens,
-                display_name=record.displayName,
-                provider_name=provider_display_name,
-                creator_name=creator_name,
-                price_tier=price_tier,  # type: ignore[arg-type]
-            )
-            costs = tuple(
-                RegistryModelCost(
-                    credit_cost=cost.creditCost,
-                    credential_provider=cost.credentialProvider,
-                    credential_id=cost.credentialId,
-                    credential_type=cost.credentialType,
-                    currency=cost.currency,
-                    metadata=_json_to_dict(cost.metadata),
-                )
-                for cost in (record.Costs or [])
-            )
-
-            # Map creator if present
-            creator = None
-            if record.Creator:
-                creator = RegistryModelCreator(
-                    id=record.Creator.id,
-                    name=record.Creator.name,
-                    display_name=record.Creator.displayName,
-                    description=record.Creator.description,
-                    website_url=record.Creator.websiteUrl,
-                    logo_url=record.Creator.logoUrl,
-                )
-
-            dynamic[record.slug] = RegistryModel(
-                slug=record.slug,
-                display_name=record.displayName,
-                description=record.description,
-                metadata=metadata,
-                capabilities=_json_to_dict(record.capabilities),
-                extra_metadata=_json_to_dict(record.metadata),
-                provider_display_name=(
-                    record.Provider.displayName
-                    if record.Provider
-                    else record.providerId
-                ),
-                is_enabled=record.isEnabled,
-                is_recommended=record.isRecommended,
-                costs=costs,
-                creator=creator,
-            )
-
-        # Atomic swap - build new structures then replace references
-        # This ensures readers never see partially updated state
-        global _dynamic_models
-        _dynamic_models = dynamic
-        _refresh_cached_schema()
-        logger.info(
-            "LLM registry refreshed with %s dynamic models (enabled: %s, disabled: %s)",
-            len(dynamic),
-            sum(1 for m in dynamic.values() if m.is_enabled),
-            sum(1 for m in dynamic.values() if not m.is_enabled),
-        )
-
-
-def _refresh_cached_schema() -> None:
-    """Refresh cached schema options and discriminator mapping."""
-    global _schema_options, _discriminator_mapping
-
-    # Build new structures
-    new_options = _build_schema_options()
-    new_mapping = {
-        slug: entry.metadata.provider for slug, entry in _dynamic_models.items()
-    }
-    for slug, metadata in _static_metadata.items():
-        new_mapping.setdefault(slug, metadata.provider)
-
-    # Atomic swap - replace references to ensure readers see consistent state
-    _schema_options = new_options
-    _discriminator_mapping = new_mapping
-
-
-def get_llm_model_metadata(slug: str) -> ModelMetadata | None:
-    """Get model metadata by slug. Checks dynamic models first, then static metadata."""
-    if slug in _dynamic_models:
-        return _dynamic_models[slug].metadata
-    return _static_metadata.get(slug)
-
-
-def get_llm_model_cost(slug: str) -> tuple[RegistryModelCost, ...]:
-    """Get model cost configuration by slug."""
-    if slug in _dynamic_models:
-        return _dynamic_models[slug].costs
-    cost_value = _static_costs.get(slug)
-    if cost_value is None:
-        return tuple()
-    return (
-        RegistryModelCost(
-            credit_cost=cost_value,
-            credential_provider="static",
-            credential_id=None,
-            credential_type=None,
-            currency=None,
-            metadata={},
-        ),
-    )
-
-
-def get_llm_model_schema_options() -> list[dict[str, str]]:
-    """
-    Get schema options for LLM model selection dropdown.
-
-    Returns a copy of cached schema options that are refreshed when the registry is
-    updated via refresh_llm_registry() (called on startup and via Redis pub/sub).
-    """
-    # Return a copy to prevent external mutation
-    return list(_schema_options)
-
-
-def get_llm_discriminator_mapping() -> dict[str, str]:
-    """
-    Get discriminator mapping for LLM models.
-
-    Returns a copy of cached discriminator mapping that is refreshed when the registry
-    is updated via refresh_llm_registry() (called on startup and via Redis pub/sub).
-    """
-    # Return a copy to prevent external mutation
-    return dict(_discriminator_mapping)
-
-
-def get_dynamic_model_slugs() -> set[str]:
-    """Get all dynamic model slugs from the registry."""
-    return set(_dynamic_models.keys())
-
-
-def get_all_model_slugs_for_validation() -> set[str]:
-    """
-    Get ALL model slugs (both enabled and disabled) for validation purposes.
-
-    This is used for JSON schema enum validation - we need to accept any known
-    model value (even disabled ones) so that existing graphs don't fail validation.
-    The actual fallback/enforcement happens at runtime in llm_call().
-    """
-    all_slugs = set(_dynamic_models.keys())
-    all_slugs.update(_static_metadata.keys())
-    return all_slugs
-
-
-def iter_dynamic_models() -> Iterable[RegistryModel]:
-    """Iterate over all dynamic models in the registry."""
-    return tuple(_dynamic_models.values())
-
-
-def get_fallback_model_for_disabled(disabled_model_slug: str) -> RegistryModel | None:
-    """
-    Find a fallback model when the requested model is disabled.
-
-    Looks for an enabled model from the same provider. Prefers models with
-    similar names or capabilities if possible.
-
-    Args:
-        disabled_model_slug: The slug of the disabled model
-
-    Returns:
-        An enabled RegistryModel from the same provider, or None if no fallback found
-    """
-    disabled_model = _dynamic_models.get(disabled_model_slug)
-    if not disabled_model:
-        return None
-
-    provider = disabled_model.metadata.provider
-
-    # Find all enabled models from the same provider
-    candidates = [
-        model
-        for model in _dynamic_models.values()
-        if model.is_enabled and model.metadata.provider == provider
-    ]
-
-    if not candidates:
-        return None
-
-    # Sort by: prefer models with similar context window, then by name
-    candidates.sort(
-        key=lambda m: (
-            abs(m.metadata.context_window - disabled_model.metadata.context_window),
-            m.display_name.lower(),
-        )
-    )
-
-    return candidates[0]
-
-
-def is_model_enabled(model_slug: str) -> bool:
-    """Check if a model is enabled in the registry."""
-    model = _dynamic_models.get(model_slug)
-    if not model:
-        # Model not in registry - assume it's a static/legacy model and allow it
-        return True
-    return model.is_enabled
-
-
-def get_model_info(model_slug: str) -> RegistryModel | None:
-    """Get model info from the registry."""
-    return _dynamic_models.get(model_slug)
-
-
-def get_default_model_slug() -> str | None:
-    """
-    Get the default model slug to use for block defaults.
-
-    Returns the recommended model if set (configured via admin UI),
-    otherwise returns the first enabled model alphabetically.
-    Returns None if no models are available or enabled.
-    """
-    # Return the recommended model if one is set and enabled
-    for model in _dynamic_models.values():
-        if model.is_recommended and model.is_enabled:
-            return model.slug
-
-    # No recommended model set - find first enabled model alphabetically
-    for model in sorted(_dynamic_models.values(), key=lambda m: m.display_name.lower()):
-        if model.is_enabled:
-            logger.warning(
-                "No recommended model set, using '%s' as default",
-                model.slug,
-            )
-            return model.slug
-
-    # No enabled models available
-    if _dynamic_models:
-        logger.error(
-            "No enabled models found in registry (%d models registered but all disabled)",
-            len(_dynamic_models),
-        )
-    else:
-        logger.error("No models registered in LLM registry")
-
-    return None

autogpt_platform/backend/backend/data/llm_registry/schema_utils.py

@@ -1,130 +0,0 @@
-"""
-Helper utilities for LLM registry integration with block schemas.
-
-This module handles the dynamic injection of discriminator mappings
-and model options from the LLM registry into block schemas.
-"""
-
-import logging
-from typing import Any
-
-from backend.data.llm_registry.registry import (
-    get_all_model_slugs_for_validation,
-    get_default_model_slug,
-    get_llm_discriminator_mapping,
-    get_llm_model_schema_options,
-)
-
-logger = logging.getLogger(__name__)
-
-
-def is_llm_model_field(field_name: str, field_info: Any) -> bool:
-    """
-    Check if a field is an LLM model selection field.
-
-    Returns True if the field has 'options' in json_schema_extra
-    (set by llm_model_schema_extra() in blocks/llm.py).
-    """
-    if not hasattr(field_info, "json_schema_extra"):
-        return False
-
-    extra = field_info.json_schema_extra
-    if isinstance(extra, dict):
-        return "options" in extra
-
-    return False
-
-
-def refresh_llm_model_options(field_schema: dict[str, Any]) -> None:
-    """
-    Refresh LLM model options from the registry.
-
-    Updates 'options' (for frontend dropdown) to show only enabled models,
-    but keeps the 'enum' (for validation) inclusive of ALL known models.
-
-    This is important because:
-    - Options: What users see in the dropdown (enabled models only)
-    - Enum: What values pass validation (all known models, including disabled)
-
-    Existing graphs may have disabled models selected - they should pass validation
-    and the fallback logic in llm_call() will handle using an alternative model.
-    """
-    fresh_options = get_llm_model_schema_options()
-    if not fresh_options:
-        return
-
-    # Update options array (UI dropdown) - only enabled models
-    if "options" in field_schema:
-        field_schema["options"] = fresh_options
-
-    all_known_slugs = get_all_model_slugs_for_validation()
-    if all_known_slugs and "enum" in field_schema:
-        existing_enum = set(field_schema.get("enum", []))
-        combined_enum = existing_enum | all_known_slugs
-        field_schema["enum"] = sorted(combined_enum)
-
-    # Set the default value from the registry (gpt-4o if available, else first enabled)
-    # This ensures new blocks have a sensible default pre-selected
-    default_slug = get_default_model_slug()
-    if default_slug:
-        field_schema["default"] = default_slug
-
-
-def refresh_llm_discriminator_mapping(field_schema: dict[str, Any]) -> None:
-    """
-    Refresh discriminator_mapping for fields that use model-based discrimination.
-
-    The discriminator is already set when AICredentialsField() creates the field.
-    We only need to refresh the mapping when models are added/removed.
-    """
-    if field_schema.get("discriminator") != "model":
-        return
-
-    # Always refresh the mapping to get latest models
-    fresh_mapping = get_llm_discriminator_mapping()
-    if fresh_mapping is not None:
-        field_schema["discriminator_mapping"] = fresh_mapping
-
-
-def update_schema_with_llm_registry(
-    schema: dict[str, Any], model_class: type | None = None
-) -> None:
-    """
-    Update a JSON schema with current LLM registry data.
-
-    Refreshes:
-    1. Model options for LLM model selection fields (dropdown choices)
-    2. Discriminator mappings for credentials fields (model → provider)
-
-    Args:
-        schema: The JSON schema to update (mutated in-place)
-        model_class: The Pydantic model class (optional, for field introspection)
-    """
-    properties = schema.get("properties", {})
-
-    for field_name, field_schema in properties.items():
-        if not isinstance(field_schema, dict):
-            continue
-
-        # Refresh model options for LLM model fields
-        if model_class and hasattr(model_class, "model_fields"):
-            field_info = model_class.model_fields.get(field_name)
-            if field_info and is_llm_model_field(field_name, field_info):
-                try:
-                    refresh_llm_model_options(field_schema)
-                except Exception as exc:
-                    logger.warning(
-                        "Failed to refresh LLM options for field %s: %s",
-                        field_name,
-                        exc,
-                    )
-
-        # Refresh discriminator mapping for fields that use model discrimination
-        try:
-            refresh_llm_discriminator_mapping(field_schema)
-        except Exception as exc:
-            logger.warning(
-                "Failed to refresh discriminator mapping for field %s: %s",
-                field_name,
-                exc,
-            )

autogpt_platform/backend/backend/data/model.py

@@ -39,7 +39,6 @@ from pydantic_core import (
 )
 from typing_extensions import TypedDict
 
-from backend.data.llm_registry import update_schema_with_llm_registry
 from backend.integrations.providers import ProviderName
 from backend.util.json import loads as json_loads
 from backend.util.request import parse_url
@@ -551,9 +550,7 @@ class CredentialsMetaInput(BaseModel, Generic[CP, CT]):
             else:
                 schema["credentials_provider"] = allowed_providers
             schema["credentials_types"] = model_class.allowed_cred_types()
-
-        # Ensure LLM discriminators are populated (delegates to shared helper)
-        update_schema_with_llm_registry(schema, model_class)
+        # Do not return anything, just mutate schema in place
 
     model_config = ConfigDict(
         json_schema_extra=_add_json_schema_extra,  # type: ignore
@@ -708,20 +705,16 @@ def CredentialsField(
     This is enforced by the `BlockSchema` base class.
     """
 
-    # Build field_schema_extra - always include discriminator and mapping if discriminator is set
-    field_schema_extra: dict[str, Any] = {}
-
-    # Always include discriminator if provided
-    if discriminator is not None:
-        field_schema_extra["discriminator"] = discriminator
-        # Always include discriminator_mapping when discriminator is set (even if empty initially)
-        field_schema_extra["discriminator_mapping"] = discriminator_mapping or {}
-
-    # Include other optional fields (only if not None)
-    if required_scopes:
-        field_schema_extra["credentials_scopes"] = list(required_scopes)
-    if discriminator_values:
-        field_schema_extra["discriminator_values"] = discriminator_values
+    field_schema_extra = {
+        k: v
+        for k, v in {
+            "credentials_scopes": list(required_scopes) or None,
+            "discriminator": discriminator,
+            "discriminator_mapping": discriminator_mapping,
+            "discriminator_values": discriminator_values,
+        }.items()
+        if v is not None
+    }
 
     # Merge any json_schema_extra passed in kwargs
     if "json_schema_extra" in kwargs:

autogpt_platform/backend/backend/executor/llm_registry_init.py

@@ -1,67 +0,0 @@
-"""
-Helper functions for LLM registry initialization in executor context.
-
-These functions handle refreshing the LLM registry when the executor starts
-and subscribing to real-time updates via Redis pub/sub.
-"""
-
-import logging
-
-from backend.blocks._base import BlockSchema
-from backend.data import db, llm_registry
-from backend.data.block import initialize_blocks
-from backend.data.block_cost_config import refresh_llm_costs
-from backend.data.llm_registry import subscribe_to_registry_refresh
-
-logger = logging.getLogger(__name__)
-
-
-async def initialize_registry_for_executor() -> None:
-    """
-    Initialize blocks and refresh LLM registry in the executor context.
-
-    This must run in the executor's event loop to have access to the database.
-    """
-    try:
-        # Connect to database if not already connected
-        if not db.is_connected():
-            await db.connect()
-            logger.info("[GraphExecutor] Connected to database for registry refresh")
-
-        # Initialize blocks (internally refreshes LLM registry and costs)
-        await initialize_blocks()
-        logger.info("[GraphExecutor] Blocks initialized")
-    except Exception as exc:
-        logger.warning(
-            "[GraphExecutor] Failed to refresh LLM registry on startup: %s",
-            exc,
-            exc_info=True,
-        )
-
-
-async def refresh_registry_on_notification() -> None:
-    """Refresh LLM registry when notified via Redis pub/sub."""
-    try:
-        # Ensure DB is connected
-        if not db.is_connected():
-            await db.connect()
-
-        # Refresh registry and costs
-        await llm_registry.refresh_llm_registry()
-        await refresh_llm_costs()
-
-        # Clear block schema caches so they regenerate with new model options
-        BlockSchema.clear_all_schema_caches()
-
-        logger.info("[GraphExecutor] LLM registry refreshed from notification")
-    except Exception as exc:
-        logger.error(
-            "[GraphExecutor] Failed to refresh LLM registry from notification: %s",
-            exc,
-            exc_info=True,
-        )
-
-
-async def subscribe_to_registry_updates() -> None:
-    """Subscribe to Redis pub/sub for LLM registry refresh notifications."""
-    await subscribe_to_registry_refresh(refresh_registry_on_notification)

autogpt_platform/backend/backend/executor/manager.py

@@ -708,20 +708,6 @@ class ExecutionProcessor:
         )
         self.node_execution_thread.start()
         self.node_evaluation_thread.start()
-
-        # Initialize LLM registry and subscribe to updates
-        from backend.executor.llm_registry_init import (
-            initialize_registry_for_executor,
-            subscribe_to_registry_updates,
-        )
-
-        asyncio.run_coroutine_threadsafe(
-            initialize_registry_for_executor(), self.node_execution_loop
-        )
-        asyncio.run_coroutine_threadsafe(
-            subscribe_to_registry_updates(), self.node_execution_loop
-        )
-
         logger.info(f"[GraphExecutor] {self.tid} started")
 
     @error_logged(swallow=False)

autogpt_platform/backend/backend/server/v2/llm/db.py

@@ -1,941 +0,0 @@
-from __future__ import annotations
-
-from typing import Any, Iterable, Sequence, cast
-
-import prisma
-import prisma.models
-
-from backend.data.db import transaction
-from backend.server.v2.llm import model as llm_model
-from backend.util.models import Pagination
-
-
-def _json_dict(value: Any | None) -> dict[str, Any]:
-    if not value:
-        return {}
-    if isinstance(value, dict):
-        return value
-    return {}
-
-
-def _map_cost(record: prisma.models.LlmModelCost) -> llm_model.LlmModelCost:
-    return llm_model.LlmModelCost(
-        id=record.id,
-        unit=record.unit,
-        credit_cost=record.creditCost,
-        credential_provider=record.credentialProvider,
-        credential_id=record.credentialId,
-        credential_type=record.credentialType,
-        currency=record.currency,
-        metadata=_json_dict(record.metadata),
-    )
-
-
-def _map_creator(
-    record: prisma.models.LlmModelCreator,
-) -> llm_model.LlmModelCreator:
-    return llm_model.LlmModelCreator(
-        id=record.id,
-        name=record.name,
-        display_name=record.displayName,
-        description=record.description,
-        website_url=record.websiteUrl,
-        logo_url=record.logoUrl,
-        metadata=_json_dict(record.metadata),
-    )
-
-
-def _map_model(record: prisma.models.LlmModel) -> llm_model.LlmModel:
-    costs = []
-    if record.Costs:
-        costs = [_map_cost(cost) for cost in record.Costs]
-
-    creator = None
-    if hasattr(record, "Creator") and record.Creator:
-        creator = _map_creator(record.Creator)
-
-    return llm_model.LlmModel(
-        id=record.id,
-        slug=record.slug,
-        display_name=record.displayName,
-        description=record.description,
-        provider_id=record.providerId,
-        creator_id=record.creatorId,
-        creator=creator,
-        context_window=record.contextWindow,
-        max_output_tokens=record.maxOutputTokens,
-        is_enabled=record.isEnabled,
-        is_recommended=record.isRecommended,
-        capabilities=_json_dict(record.capabilities),
-        metadata=_json_dict(record.metadata),
-        costs=costs,
-    )
-
-
-def _map_provider(record: prisma.models.LlmProvider) -> llm_model.LlmProvider:
-    models: list[llm_model.LlmModel] = []
-    if record.Models:
-        models = [_map_model(model) for model in record.Models]
-
-    return llm_model.LlmProvider(
-        id=record.id,
-        name=record.name,
-        display_name=record.displayName,
-        description=record.description,
-        default_credential_provider=record.defaultCredentialProvider,
-        default_credential_id=record.defaultCredentialId,
-        default_credential_type=record.defaultCredentialType,
-        supports_tools=record.supportsTools,
-        supports_json_output=record.supportsJsonOutput,
-        supports_reasoning=record.supportsReasoning,
-        supports_parallel_tool=record.supportsParallelTool,
-        metadata=_json_dict(record.metadata),
-        models=models,
-    )
-
-
-async def list_providers(
-    include_models: bool = True, enabled_only: bool = False
-) -> list[llm_model.LlmProvider]:
-    """
-    List all LLM providers.
-
-    Args:
-        include_models: Whether to include models for each provider
-        enabled_only: If True, only include enabled models (for public routes)
-    """
-    include: Any = None
-    if include_models:
-        model_where = {"isEnabled": True} if enabled_only else None
-        include = {
-            "Models": {
-                "include": {"Costs": True, "Creator": True},
-                "where": model_where,
-            }
-        }
-    records = await prisma.models.LlmProvider.prisma().find_many(include=include)
-    return [_map_provider(record) for record in records]
-
-
-async def upsert_provider(
-    request: llm_model.UpsertLlmProviderRequest,
-    provider_id: str | None = None,
-) -> llm_model.LlmProvider:
-    data: Any = {
-        "name": request.name,
-        "displayName": request.display_name,
-        "description": request.description,
-        "defaultCredentialProvider": request.default_credential_provider,
-        "defaultCredentialId": request.default_credential_id,
-        "defaultCredentialType": request.default_credential_type,
-        "supportsTools": request.supports_tools,
-        "supportsJsonOutput": request.supports_json_output,
-        "supportsReasoning": request.supports_reasoning,
-        "supportsParallelTool": request.supports_parallel_tool,
-        "metadata": prisma.Json(request.metadata or {}),
-    }
-    include: Any = {"Models": {"include": {"Costs": True, "Creator": True}}}
-    if provider_id:
-        record = await prisma.models.LlmProvider.prisma().update(
-            where={"id": provider_id},
-            data=data,
-            include=include,
-        )
-    else:
-        record = await prisma.models.LlmProvider.prisma().create(
-            data=data,
-            include=include,
-        )
-    if record is None:
-        raise ValueError("Failed to create/update provider")
-    return _map_provider(record)
-
-
-async def delete_provider(provider_id: str) -> bool:
-    """
-    Delete an LLM provider.
-
-    A provider can only be deleted if it has no associated models.
-    Due to onDelete: Restrict on LlmModel.Provider, the database will
-    block deletion if models exist.
-
-    Args:
-        provider_id: UUID of the provider to delete
-
-    Returns:
-        True if deleted successfully
-
-    Raises:
-        ValueError: If provider not found or has associated models
-    """
-    # Check if provider exists
-    provider = await prisma.models.LlmProvider.prisma().find_unique(
-        where={"id": provider_id},
-        include={"Models": True},
-    )
-    if not provider:
-        raise ValueError(f"Provider with id '{provider_id}' not found")
-
-    # Check if provider has any models
-    model_count = len(provider.Models) if provider.Models else 0
-    if model_count > 0:
-        raise ValueError(
-            f"Cannot delete provider '{provider.displayName}' because it has "
-            f"{model_count} model(s). Delete all models first."
-        )
-
-    # Safe to delete
-    await prisma.models.LlmProvider.prisma().delete(where={"id": provider_id})
-    return True
-
-
-async def list_models(
-    provider_id: str | None = None,
-    enabled_only: bool = False,
-    page: int = 1,
-    page_size: int = 50,
-) -> llm_model.LlmModelsResponse:
-    """
-    List LLM models with pagination.
-
-    Args:
-        provider_id: Optional filter by provider ID
-        enabled_only: If True, only return enabled models (for public routes)
-        page: Page number (1-indexed)
-        page_size: Number of models per page
-    """
-    # Validate pagination inputs to avoid runtime errors
-    if page_size < 1:
-        page_size = 50
-    if page < 1:
-        page = 1
-
-    where: Any = {}
-    if provider_id:
-        where["providerId"] = provider_id
-    if enabled_only:
-        where["isEnabled"] = True
-
-    # Get total count for pagination
-    total_items = await prisma.models.LlmModel.prisma().count(
-        where=where if where else None
-    )
-
-    # Calculate pagination
-    skip = (page - 1) * page_size
-    total_pages = (total_items + page_size - 1) // page_size if total_items > 0 else 0
-
-    records = await prisma.models.LlmModel.prisma().find_many(
-        where=where if where else None,
-        include={"Costs": True, "Creator": True},
-        skip=skip,
-        take=page_size,
-    )
-    models = [_map_model(record) for record in records]
-
-    return llm_model.LlmModelsResponse(
-        models=models,
-        pagination=Pagination(
-            total_items=total_items,
-            total_pages=total_pages,
-            current_page=page,
-            page_size=page_size,
-        ),
-    )
-
-
-def _cost_create_payload(
-    costs: Sequence[llm_model.LlmModelCostInput],
-) -> dict[str, Iterable[dict[str, Any]]]:
-
-    create_items = []
-    for cost in costs:
-        item: dict[str, Any] = {
-            "unit": cost.unit,
-            "creditCost": cost.credit_cost,
-            "credentialProvider": cost.credential_provider,
-        }
-        # Only include optional fields if they have values
-        if cost.credential_id:
-            item["credentialId"] = cost.credential_id
-        if cost.credential_type:
-            item["credentialType"] = cost.credential_type
-        if cost.currency:
-            item["currency"] = cost.currency
-        # Handle metadata - use Prisma Json type
-        if cost.metadata is not None and cost.metadata != {}:
-            item["metadata"] = prisma.Json(cost.metadata)
-        create_items.append(item)
-    return {"create": create_items}
-
-
-async def create_model(
-    request: llm_model.CreateLlmModelRequest,
-) -> llm_model.LlmModel:
-    data: Any = {
-        "slug": request.slug,
-        "displayName": request.display_name,
-        "description": request.description,
-        "Provider": {"connect": {"id": request.provider_id}},
-        "contextWindow": request.context_window,
-        "maxOutputTokens": request.max_output_tokens,
-        "isEnabled": request.is_enabled,
-        "capabilities": prisma.Json(request.capabilities or {}),
-        "metadata": prisma.Json(request.metadata or {}),
-        "Costs": _cost_create_payload(request.costs),
-    }
-    if request.creator_id:
-        data["Creator"] = {"connect": {"id": request.creator_id}}
-
-    record = await prisma.models.LlmModel.prisma().create(
-        data=data,
-        include={"Costs": True, "Creator": True, "Provider": True},
-    )
-    return _map_model(record)
-
-
-async def update_model(
-    model_id: str,
-    request: llm_model.UpdateLlmModelRequest,
-) -> llm_model.LlmModel:
-    # Build scalar field updates (non-relation fields)
-    scalar_data: Any = {}
-    if request.display_name is not None:
-        scalar_data["displayName"] = request.display_name
-    if request.description is not None:
-        scalar_data["description"] = request.description
-    if request.context_window is not None:
-        scalar_data["contextWindow"] = request.context_window
-    if request.max_output_tokens is not None:
-        scalar_data["maxOutputTokens"] = request.max_output_tokens
-    if request.is_enabled is not None:
-        scalar_data["isEnabled"] = request.is_enabled
-    if request.capabilities is not None:
-        scalar_data["capabilities"] = request.capabilities
-    if request.metadata is not None:
-        scalar_data["metadata"] = request.metadata
-    # Foreign keys can be updated directly as scalar fields
-    if request.provider_id is not None:
-        scalar_data["providerId"] = request.provider_id
-    if request.creator_id is not None:
-        # Empty string means remove the creator
-        scalar_data["creatorId"] = request.creator_id if request.creator_id else None
-
-    # If we have costs to update, we need to handle them separately
-    # because nested writes have different constraints
-    if request.costs is not None:
-        # Wrap cost replacement in a transaction for atomicity
-        async with transaction() as tx:
-            # First update scalar fields
-            if scalar_data:
-                await tx.llmmodel.update(
-                    where={"id": model_id},
-                    data=scalar_data,
-                )
-            # Then handle costs: delete existing and create new
-            await tx.llmmodelcost.delete_many(where={"llmModelId": model_id})
-            if request.costs:
-                cost_payload = _cost_create_payload(request.costs)
-                for cost_item in cost_payload["create"]:
-                    cost_item["llmModelId"] = model_id
-                    await tx.llmmodelcost.create(data=cast(Any, cost_item))
-        # Fetch the updated record (outside transaction)
-        record = await prisma.models.LlmModel.prisma().find_unique(
-            where={"id": model_id},
-            include={"Costs": True, "Creator": True},
-        )
-    else:
-        # No costs update - simple update
-        record = await prisma.models.LlmModel.prisma().update(
-            where={"id": model_id},
-            data=scalar_data,
-            include={"Costs": True, "Creator": True},
-        )
-
-    if not record:
-        raise ValueError(f"Model with id '{model_id}' not found")
-    return _map_model(record)
-
-
-async def toggle_model(
-    model_id: str,
-    is_enabled: bool,
-    migrate_to_slug: str | None = None,
-    migration_reason: str | None = None,
-    custom_credit_cost: int | None = None,
-) -> llm_model.ToggleLlmModelResponse:
-    """
-    Toggle a model's enabled status, optionally migrating workflows when disabling.
-
-    Args:
-        model_id: UUID of the model to toggle
-        is_enabled: New enabled status
-        migrate_to_slug: If disabling and this is provided, migrate all workflows
-                         using this model to the specified replacement model
-        migration_reason: Optional reason for the migration (e.g., "Provider outage")
-        custom_credit_cost: Optional custom pricing override for migrated workflows.
-                           When set, the billing system should use this cost instead
-                           of the target model's cost for affected nodes.
-
-    Returns:
-        ToggleLlmModelResponse with the updated model and optional migration stats
-    """
-    import json
-
-    # Get the model being toggled
-    model = await prisma.models.LlmModel.prisma().find_unique(
-        where={"id": model_id}, include={"Costs": True}
-    )
-    if not model:
-        raise ValueError(f"Model with id '{model_id}' not found")
-
-    nodes_migrated = 0
-    migration_id: str | None = None
-
-    # If disabling with migration, perform migration first
-    if not is_enabled and migrate_to_slug:
-        # Validate replacement model exists and is enabled
-        replacement = await prisma.models.LlmModel.prisma().find_unique(
-            where={"slug": migrate_to_slug}
-        )
-        if not replacement:
-            raise ValueError(f"Replacement model '{migrate_to_slug}' not found")
-        if not replacement.isEnabled:
-            raise ValueError(
-                f"Replacement model '{migrate_to_slug}' is disabled. "
-                f"Please enable it before using it as a replacement."
-            )
-
-        # Perform all operations atomically within a single transaction
-        # This ensures no nodes are missed between query and update
-        async with transaction() as tx:
-            # Get the IDs of nodes that will be migrated (inside transaction for consistency)
-            node_ids_result = await tx.query_raw(
-                """
-                SELECT id
-                FROM "AgentNode"
-                WHERE "constantInput"::jsonb->>'model' = $1
-                FOR UPDATE
-                """,
-                model.slug,
-            )
-            migrated_node_ids = (
-                [row["id"] for row in node_ids_result] if node_ids_result else []
-            )
-            nodes_migrated = len(migrated_node_ids)
-
-            if nodes_migrated > 0:
-                # Update by IDs to ensure we only update the exact nodes we queried
-                # Use JSON array and jsonb_array_elements_text for safe parameterization
-                node_ids_json = json.dumps(migrated_node_ids)
-                await tx.execute_raw(
-                    """
-                    UPDATE "AgentNode"
-                    SET "constantInput" = JSONB_SET(
-                        "constantInput"::jsonb,
-                        '{model}',
-                        to_jsonb($1::text)
-                    )
-                    WHERE id::text IN (
-                        SELECT jsonb_array_elements_text($2::jsonb)
-                    )
-                    """,
-                    migrate_to_slug,
-                    node_ids_json,
-                )
-
-            record = await tx.llmmodel.update(
-                where={"id": model_id},
-                data={"isEnabled": is_enabled},
-                include={"Costs": True},
-            )
-
-            # Create migration record for revert capability
-            if nodes_migrated > 0:
-                migration_data: Any = {
-                    "sourceModelSlug": model.slug,
-                    "targetModelSlug": migrate_to_slug,
-                    "reason": migration_reason,
-                    "migratedNodeIds": json.dumps(migrated_node_ids),
-                    "nodeCount": nodes_migrated,
-                    "customCreditCost": custom_credit_cost,
-                }
-                migration_record = await tx.llmmodelmigration.create(
-                    data=migration_data
-                )
-                migration_id = migration_record.id
-    else:
-        # Simple toggle without migration
-        record = await prisma.models.LlmModel.prisma().update(
-            where={"id": model_id},
-            data={"isEnabled": is_enabled},
-            include={"Costs": True},
-        )
-
-    if record is None:
-        raise ValueError(f"Model with id '{model_id}' not found")
-    return llm_model.ToggleLlmModelResponse(
-        model=_map_model(record),
-        nodes_migrated=nodes_migrated,
-        migrated_to_slug=migrate_to_slug if nodes_migrated > 0 else None,
-        migration_id=migration_id,
-    )
-
-
-async def get_model_usage(model_id: str) -> llm_model.LlmModelUsageResponse:
-    """Get usage count for a model."""
-    import prisma as prisma_module
-
-    model = await prisma.models.LlmModel.prisma().find_unique(where={"id": model_id})
-    if not model:
-        raise ValueError(f"Model with id '{model_id}' not found")
-
-    count_result = await prisma_module.get_client().query_raw(
-        """
-        SELECT COUNT(*) as count
-        FROM "AgentNode"
-        WHERE "constantInput"::jsonb->>'model' = $1
-        """,
-        model.slug,
-    )
-    node_count = int(count_result[0]["count"]) if count_result else 0
-
-    return llm_model.LlmModelUsageResponse(model_slug=model.slug, node_count=node_count)
-
-
-async def delete_model(
-    model_id: str, replacement_model_slug: str | None = None
-) -> llm_model.DeleteLlmModelResponse:
-    """
-    Delete a model and optionally migrate all AgentNodes using it to a replacement model.
-
-    This performs an atomic operation within a database transaction:
-    1. Validates the model exists
-    2. Counts affected nodes
-    3. If nodes exist, validates replacement model and migrates them
-    4. Deletes the LlmModel record (CASCADE deletes costs)
-
-    Args:
-        model_id: UUID of the model to delete
-        replacement_model_slug: Slug of the model to migrate to (required only if nodes use this model)
-
-    Returns:
-        DeleteLlmModelResponse with migration stats
-
-    Raises:
-        ValueError: If model not found, nodes exist but no replacement provided,
-                    replacement not found, or replacement is disabled
-    """
-    # 1. Get the model being deleted (early validation - outside transaction)
-    model = await prisma.models.LlmModel.prisma().find_unique(
-        where={"id": model_id}, include={"Costs": True}
-    )
-    if not model:
-        raise ValueError(f"Model with id '{model_id}' not found")
-
-    deleted_slug = model.slug
-    deleted_display_name = model.displayName
-
-    # 2. Perform all mutation logic atomically within a transaction
-    # This prevents TOCTOU issues where nodes could be created between count and delete
-    async with transaction() as tx:
-        # Count affected nodes inside the transaction
-        count_result = await tx.query_raw(
-            """
-            SELECT COUNT(*) as count
-            FROM "AgentNode"
-            WHERE "constantInput"::jsonb->>'model' = $1
-            """,
-            deleted_slug,
-        )
-        nodes_to_migrate = int(count_result[0]["count"]) if count_result else 0
-
-        # Validate replacement model only if there are nodes to migrate
-        if nodes_to_migrate > 0:
-            if not replacement_model_slug:
-                raise ValueError(
-                    f"Cannot delete model '{deleted_slug}': {nodes_to_migrate} workflow node(s) "
-                    f"are using it. Please provide a replacement_model_slug to migrate them."
-                )
-            replacement = await tx.llmmodel.find_unique(
-                where={"slug": replacement_model_slug}
-            )
-            if not replacement:
-                raise ValueError(
-                    f"Replacement model '{replacement_model_slug}' not found"
-                )
-            if not replacement.isEnabled:
-                raise ValueError(
-                    f"Replacement model '{replacement_model_slug}' is disabled. "
-                    f"Please enable it before using it as a replacement."
-                )
-
-            # Migrate all AgentNode.constantInput->model to replacement
-            await tx.execute_raw(
-                """
-                UPDATE "AgentNode"
-                SET "constantInput" = JSONB_SET(
-                    "constantInput"::jsonb,
-                    '{model}',
-                    to_jsonb($1::text)
-                )
-                WHERE "constantInput"::jsonb->>'model' = $2
-                """,
-                replacement_model_slug,
-                deleted_slug,
-            )
-
-        # Delete the model (CASCADE will delete costs automatically)
-        await tx.llmmodel.delete(where={"id": model_id})
-
-    # Build appropriate message based on whether migration happened
-    if nodes_to_migrate > 0:
-        message = (
-            f"Successfully deleted model '{deleted_display_name}' ({deleted_slug}) "
-            f"and migrated {nodes_to_migrate} workflow node(s) to '{replacement_model_slug}'."
-        )
-    else:
-        message = (
-            f"Successfully deleted model '{deleted_display_name}' ({deleted_slug}). "
-            f"No workflows were using this model."
-        )
-
-    return llm_model.DeleteLlmModelResponse(
-        deleted_model_slug=deleted_slug,
-        deleted_model_display_name=deleted_display_name,
-        replacement_model_slug=replacement_model_slug,
-        nodes_migrated=nodes_to_migrate,
-        message=message,
-    )
-
-
-def _map_migration(
-    record: prisma.models.LlmModelMigration,
-) -> llm_model.LlmModelMigration:
-    return llm_model.LlmModelMigration(
-        id=record.id,
-        source_model_slug=record.sourceModelSlug,
-        target_model_slug=record.targetModelSlug,
-        reason=record.reason,
-        node_count=record.nodeCount,
-        custom_credit_cost=record.customCreditCost,
-        is_reverted=record.isReverted,
-        created_at=record.createdAt,
-        reverted_at=record.revertedAt,
-    )
-
-
-async def list_migrations(
-    include_reverted: bool = False,
-) -> list[llm_model.LlmModelMigration]:
-    """
-    List model migrations, optionally including reverted ones.
-
-    Args:
-        include_reverted: If True, include reverted migrations. Default is False.
-
-    Returns:
-        List of LlmModelMigration records
-    """
-    where: Any = None if include_reverted else {"isReverted": False}
-    records = await prisma.models.LlmModelMigration.prisma().find_many(
-        where=where,
-        order={"createdAt": "desc"},
-    )
-    return [_map_migration(record) for record in records]
-
-
-async def get_migration(migration_id: str) -> llm_model.LlmModelMigration | None:
-    """Get a specific migration by ID."""
-    record = await prisma.models.LlmModelMigration.prisma().find_unique(
-        where={"id": migration_id}
-    )
-    return _map_migration(record) if record else None
-
-
-async def revert_migration(
-    migration_id: str,
-    re_enable_source_model: bool = True,
-) -> llm_model.RevertMigrationResponse:
-    """
-    Revert a model migration, restoring affected nodes to their original model.
-
-    This only reverts the specific nodes that were migrated, not all nodes
-    currently using the target model.
-
-    Args:
-        migration_id: UUID of the migration to revert
-        re_enable_source_model: Whether to re-enable the source model if it's disabled
-
-    Returns:
-        RevertMigrationResponse with revert stats
-
-    Raises:
-        ValueError: If migration not found, already reverted, or source model not available
-    """
-    import json
-    from datetime import datetime, timezone
-
-    # Get the migration record
-    migration = await prisma.models.LlmModelMigration.prisma().find_unique(
-        where={"id": migration_id}
-    )
-    if not migration:
-        raise ValueError(f"Migration with id '{migration_id}' not found")
-
-    if migration.isReverted:
-        raise ValueError(
-            f"Migration '{migration_id}' has already been reverted "
-            f"on {migration.revertedAt.isoformat() if migration.revertedAt else 'unknown date'}"
-        )
-
-    # Check if source model exists
-    source_model = await prisma.models.LlmModel.prisma().find_unique(
-        where={"slug": migration.sourceModelSlug}
-    )
-    if not source_model:
-        raise ValueError(
-            f"Source model '{migration.sourceModelSlug}' no longer exists. "
-            f"Cannot revert migration."
-        )
-
-    # Get the migrated node IDs (Prisma auto-parses JSONB to list)
-    migrated_node_ids: list[str] = (
-        migration.migratedNodeIds
-        if isinstance(migration.migratedNodeIds, list)
-        else json.loads(migration.migratedNodeIds)  # type: ignore
-    )
-    if not migrated_node_ids:
-        raise ValueError("No nodes to revert in this migration")
-
-    # Track if we need to re-enable the source model
-    source_model_was_disabled = not source_model.isEnabled
-    should_re_enable = source_model_was_disabled and re_enable_source_model
-    source_model_re_enabled = False
-
-    # Perform revert atomically
-    async with transaction() as tx:
-        # Re-enable the source model if requested and it was disabled
-        if should_re_enable:
-            await tx.llmmodel.update(
-                where={"id": source_model.id},
-                data={"isEnabled": True},
-            )
-            source_model_re_enabled = True
-
-        # Update only the specific nodes that were migrated
-        # We need to check that they still have the target model (haven't been changed since)
-        # Use a single batch update for efficiency
-        # Use JSON array and jsonb_array_elements_text for safe parameterization
-        node_ids_json = json.dumps(migrated_node_ids)
-        result = await tx.execute_raw(
-            """
-            UPDATE "AgentNode"
-            SET "constantInput" = JSONB_SET(
-                "constantInput"::jsonb,
-                '{model}',
-                to_jsonb($1::text)
-            )
-            WHERE id::text IN (
-                SELECT jsonb_array_elements_text($2::jsonb)
-            )
-            AND "constantInput"::jsonb->>'model' = $3
-            """,
-            migration.sourceModelSlug,
-            node_ids_json,
-            migration.targetModelSlug,
-        )
-        nodes_reverted = result if result else 0
-
-        # Mark migration as reverted
-        await tx.llmmodelmigration.update(
-            where={"id": migration_id},
-            data={
-                "isReverted": True,
-                "revertedAt": datetime.now(timezone.utc),
-            },
-        )
-
-    # Calculate nodes that were already changed since migration
-    nodes_already_changed = len(migrated_node_ids) - nodes_reverted
-
-    # Build appropriate message
-    message_parts = [
-        f"Successfully reverted migration: {nodes_reverted} node(s) restored "
-        f"from '{migration.targetModelSlug}' to '{migration.sourceModelSlug}'."
-    ]
-    if nodes_already_changed > 0:
-        message_parts.append(
-            f" {nodes_already_changed} node(s) were already changed and not reverted."
-        )
-    if source_model_re_enabled:
-        message_parts.append(
-            f" Model '{migration.sourceModelSlug}' has been re-enabled."
-        )
-
-    return llm_model.RevertMigrationResponse(
-        migration_id=migration_id,
-        source_model_slug=migration.sourceModelSlug,
-        target_model_slug=migration.targetModelSlug,
-        nodes_reverted=nodes_reverted,
-        nodes_already_changed=nodes_already_changed,
-        source_model_re_enabled=source_model_re_enabled,
-        message="".join(message_parts),
-    )
-
-
-# ============================================================================
-# Creator CRUD operations
-# ============================================================================
-
-
-async def list_creators() -> list[llm_model.LlmModelCreator]:
-    """List all LLM model creators."""
-    records = await prisma.models.LlmModelCreator.prisma().find_many(
-        order={"displayName": "asc"}
-    )
-    return [_map_creator(record) for record in records]
-
-
-async def get_creator(creator_id: str) -> llm_model.LlmModelCreator | None:
-    """Get a specific creator by ID."""
-    record = await prisma.models.LlmModelCreator.prisma().find_unique(
-        where={"id": creator_id}
-    )
-    return _map_creator(record) if record else None
-
-
-async def upsert_creator(
-    request: llm_model.UpsertLlmCreatorRequest,
-    creator_id: str | None = None,
-) -> llm_model.LlmModelCreator:
-    """Create or update a model creator."""
-    data: Any = {
-        "name": request.name,
-        "displayName": request.display_name,
-        "description": request.description,
-        "websiteUrl": request.website_url,
-        "logoUrl": request.logo_url,
-        "metadata": prisma.Json(request.metadata or {}),
-    }
-    if creator_id:
-        record = await prisma.models.LlmModelCreator.prisma().update(
-            where={"id": creator_id},
-            data=data,
-        )
-    else:
-        record = await prisma.models.LlmModelCreator.prisma().create(data=data)
-    if record is None:
-        raise ValueError("Failed to create/update creator")
-    return _map_creator(record)
-
-
-async def delete_creator(creator_id: str) -> bool:
-    """
-    Delete a model creator.
-
-    This will set creatorId to NULL on all associated models (due to onDelete: SetNull).
-
-    Args:
-        creator_id: UUID of the creator to delete
-
-    Returns:
-        True if deleted successfully
-
-    Raises:
-        ValueError: If creator not found
-    """
-    creator = await prisma.models.LlmModelCreator.prisma().find_unique(
-        where={"id": creator_id}
-    )
-    if not creator:
-        raise ValueError(f"Creator with id '{creator_id}' not found")
-
-    await prisma.models.LlmModelCreator.prisma().delete(where={"id": creator_id})
-    return True
-
-
-async def get_recommended_model() -> llm_model.LlmModel | None:
-    """
-    Get the currently recommended LLM model.
-
-    Returns:
-        The recommended model, or None if no model is marked as recommended.
-    """
-    record = await prisma.models.LlmModel.prisma().find_first(
-        where={"isRecommended": True, "isEnabled": True},
-        include={"Costs": True, "Creator": True},
-    )
-    return _map_model(record) if record else None
-
-
-async def set_recommended_model(
-    model_id: str,
-) -> tuple[llm_model.LlmModel, str | None]:
-    """
-    Set a model as the recommended model.
-
-    This will clear the isRecommended flag from any other model and set it
-    on the specified model. The model must be enabled.
-
-    Args:
-        model_id: UUID of the model to set as recommended
-
-    Returns:
-        Tuple of (the updated model, previous recommended model slug or None)
-
-    Raises:
-        ValueError: If model not found or not enabled
-    """
-    # First, verify the model exists and is enabled
-    target_model = await prisma.models.LlmModel.prisma().find_unique(
-        where={"id": model_id}
-    )
-    if not target_model:
-        raise ValueError(f"Model with id '{model_id}' not found")
-    if not target_model.isEnabled:
-        raise ValueError(
-            f"Cannot set disabled model '{target_model.slug}' as recommended"
-        )
-
-    # Get the current recommended model (if any)
-    current_recommended = await prisma.models.LlmModel.prisma().find_first(
-        where={"isRecommended": True}
-    )
-    previous_slug = current_recommended.slug if current_recommended else None
-
-    # Use a transaction to ensure atomicity
-    async with transaction() as tx:
-        # Clear isRecommended from all models
-        await tx.llmmodel.update_many(
-            where={"isRecommended": True},
-            data={"isRecommended": False},
-        )
-        # Set the new recommended model
-        await tx.llmmodel.update(
-            where={"id": model_id},
-            data={"isRecommended": True},
-        )
-
-    # Fetch and return the updated model
-    updated_record = await prisma.models.LlmModel.prisma().find_unique(
-        where={"id": model_id},
-        include={"Costs": True, "Creator": True},
-    )
-    if not updated_record:
-        raise ValueError("Failed to fetch updated model")
-
-    return _map_model(updated_record), previous_slug
-
-
-async def get_recommended_model_slug() -> str | None:
-    """
-    Get the slug of the currently recommended LLM model.
-
-    Returns:
-        The slug of the recommended model, or None if no model is marked as recommended.
-    """
-    record = await prisma.models.LlmModel.prisma().find_first(
-        where={"isRecommended": True, "isEnabled": True},
-    )
-    return record.slug if record else None

autogpt_platform/backend/backend/server/v2/llm/model.py

@@ -1,235 +0,0 @@
-from __future__ import annotations
-
-import re
-from datetime import datetime
-from typing import Any, Optional
-
-import prisma.enums
-import pydantic
-
-from backend.util.models import Pagination
-
-# Pattern for valid model slugs: alphanumeric start, then alphanumeric, dots, underscores, slashes, hyphens
-SLUG_PATTERN = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9._/-]*$")
-
-
-class LlmModelCost(pydantic.BaseModel):
-    id: str
-    unit: prisma.enums.LlmCostUnit = prisma.enums.LlmCostUnit.RUN
-    credit_cost: int
-    credential_provider: str
-    credential_id: Optional[str] = None
-    credential_type: Optional[str] = None
-    currency: Optional[str] = None
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-
-
-class LlmModelCreator(pydantic.BaseModel):
-    """Represents the organization that created/trained the model (e.g., OpenAI, Meta)."""
-
-    id: str
-    name: str
-    display_name: str
-    description: Optional[str] = None
-    website_url: Optional[str] = None
-    logo_url: Optional[str] = None
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-
-
-class LlmModel(pydantic.BaseModel):
-    id: str
-    slug: str
-    display_name: str
-    description: Optional[str] = None
-    provider_id: str
-    creator_id: Optional[str] = None
-    creator: Optional[LlmModelCreator] = None
-    context_window: int
-    max_output_tokens: Optional[int] = None
-    is_enabled: bool = True
-    is_recommended: bool = False
-    capabilities: dict[str, Any] = pydantic.Field(default_factory=dict)
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-    costs: list[LlmModelCost] = pydantic.Field(default_factory=list)
-
-
-class LlmProvider(pydantic.BaseModel):
-    id: str
-    name: str
-    display_name: str
-    description: Optional[str] = None
-    default_credential_provider: Optional[str] = None
-    default_credential_id: Optional[str] = None
-    default_credential_type: Optional[str] = None
-    supports_tools: bool = True
-    supports_json_output: bool = True
-    supports_reasoning: bool = False
-    supports_parallel_tool: bool = False
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-    models: list[LlmModel] = pydantic.Field(default_factory=list)
-
-
-class LlmProvidersResponse(pydantic.BaseModel):
-    providers: list[LlmProvider]
-
-
-class LlmModelsResponse(pydantic.BaseModel):
-    models: list[LlmModel]
-    pagination: Optional[Pagination] = None
-
-
-class LlmCreatorsResponse(pydantic.BaseModel):
-    creators: list[LlmModelCreator]
-
-
-class UpsertLlmProviderRequest(pydantic.BaseModel):
-    name: str
-    display_name: str
-    description: Optional[str] = None
-    default_credential_provider: Optional[str] = None
-    default_credential_id: Optional[str] = None
-    default_credential_type: Optional[str] = "api_key"
-    supports_tools: bool = True
-    supports_json_output: bool = True
-    supports_reasoning: bool = False
-    supports_parallel_tool: bool = False
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-
-
-class UpsertLlmCreatorRequest(pydantic.BaseModel):
-    name: str
-    display_name: str
-    description: Optional[str] = None
-    website_url: Optional[str] = None
-    logo_url: Optional[str] = None
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-
-
-class LlmModelCostInput(pydantic.BaseModel):
-    unit: prisma.enums.LlmCostUnit = prisma.enums.LlmCostUnit.RUN
-    credit_cost: int
-    credential_provider: str
-    credential_id: Optional[str] = None
-    credential_type: Optional[str] = "api_key"
-    currency: Optional[str] = None
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-
-
-class CreateLlmModelRequest(pydantic.BaseModel):
-    slug: str
-    display_name: str
-    description: Optional[str] = None
-    provider_id: str
-    creator_id: Optional[str] = None
-    context_window: int
-    max_output_tokens: Optional[int] = None
-    is_enabled: bool = True
-    capabilities: dict[str, Any] = pydantic.Field(default_factory=dict)
-    metadata: dict[str, Any] = pydantic.Field(default_factory=dict)
-    costs: list[LlmModelCostInput]
-
-    @pydantic.field_validator("slug")
-    @classmethod
-    def validate_slug(cls, v: str) -> str:
-        if not v or len(v) > 100:
-            raise ValueError("Slug must be 1-100 characters")
-        if not SLUG_PATTERN.match(v):
-            raise ValueError(
-                "Slug must start with alphanumeric and contain only "
-                "alphanumeric characters, dots, underscores, slashes, or hyphens"
-            )
-        return v
-
-
-class UpdateLlmModelRequest(pydantic.BaseModel):
-    display_name: Optional[str] = None
-    description: Optional[str] = None
-    context_window: Optional[int] = None
-    max_output_tokens: Optional[int] = None
-    is_enabled: Optional[bool] = None
-    capabilities: Optional[dict[str, Any]] = None
-    metadata: Optional[dict[str, Any]] = None
-    provider_id: Optional[str] = None
-    creator_id: Optional[str] = None
-    costs: Optional[list[LlmModelCostInput]] = None
-
-
-class ToggleLlmModelRequest(pydantic.BaseModel):
-    is_enabled: bool
-    migrate_to_slug: Optional[str] = None
-    migration_reason: Optional[str] = None  # e.g., "Provider outage"
-    # Custom pricing override for migrated workflows. When set, billing should use
-    # this cost instead of the target model's cost for affected nodes.
-    # See LlmModelMigration in schema.prisma for full documentation.
-    custom_credit_cost: Optional[int] = None
-
-
-class ToggleLlmModelResponse(pydantic.BaseModel):
-    model: LlmModel
-    nodes_migrated: int = 0
-    migrated_to_slug: Optional[str] = None
-    migration_id: Optional[str] = None  # ID of the migration record for revert
-
-
-class DeleteLlmModelResponse(pydantic.BaseModel):
-    deleted_model_slug: str
-    deleted_model_display_name: str
-    replacement_model_slug: Optional[str] = None
-    nodes_migrated: int
-    message: str
-
-
-class LlmModelUsageResponse(pydantic.BaseModel):
-    model_slug: str
-    node_count: int
-
-
-# Migration tracking models
-class LlmModelMigration(pydantic.BaseModel):
-    id: str
-    source_model_slug: str
-    target_model_slug: str
-    reason: Optional[str] = None
-    node_count: int
-    # Custom pricing override - billing should use this instead of target model's cost
-    custom_credit_cost: Optional[int] = None
-    is_reverted: bool = False
-    created_at: datetime
-    reverted_at: Optional[datetime] = None
-
-
-class LlmMigrationsResponse(pydantic.BaseModel):
-    migrations: list[LlmModelMigration]
-
-
-class RevertMigrationRequest(pydantic.BaseModel):
-    re_enable_source_model: bool = (
-        True  # Whether to re-enable the source model if disabled
-    )
-
-
-class RevertMigrationResponse(pydantic.BaseModel):
-    migration_id: str
-    source_model_slug: str
-    target_model_slug: str
-    nodes_reverted: int
-    nodes_already_changed: int = (
-        0  # Nodes that were modified since migration (not reverted)
-    )
-    source_model_re_enabled: bool = False  # Whether the source model was re-enabled
-    message: str
-
-
-class SetRecommendedModelRequest(pydantic.BaseModel):
-    model_id: str
-
-
-class SetRecommendedModelResponse(pydantic.BaseModel):
-    model: LlmModel
-    previous_recommended_slug: Optional[str] = None
-    message: str
-
-
-class RecommendedModelResponse(pydantic.BaseModel):
-    model: Optional[LlmModel] = None
-    slug: Optional[str] = None

autogpt_platform/backend/backend/server/v2/llm/routes.py

@@ -1,29 +0,0 @@
-import autogpt_libs.auth
-import fastapi
-
-from backend.server.v2.llm import db as llm_db
-from backend.server.v2.llm import model as llm_model
-
-router = fastapi.APIRouter(
-    prefix="/llm",
-    tags=["llm"],
-    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
-)
-
-
-@router.get("/models", response_model=llm_model.LlmModelsResponse)
-async def list_models(
-    page: int = fastapi.Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = fastapi.Query(
-        default=50, ge=1, le=100, description="Number of models per page"
-    ),
-):
-    """List all enabled LLM models available to users."""
-    return await llm_db.list_models(enabled_only=True, page=page, page_size=page_size)
-
-
-@router.get("/providers", response_model=llm_model.LlmProvidersResponse)
-async def list_providers():
-    """List all LLM providers with their enabled models."""
-    providers = await llm_db.list_providers(include_models=True, enabled_only=True)
-    return llm_model.LlmProvidersResponse(providers=providers)

autogpt_platform/backend/backend/util/settings.py

@@ -662,6 +662,17 @@ class Secrets(UpdateTrackingModel["Secrets"], BaseSettings):
     mem0_api_key: str = Field(default="", description="Mem0 API key")
     elevenlabs_api_key: str = Field(default="", description="ElevenLabs API key")
 
+    linear_api_key: str = Field(
+        default="", description="Linear API key for system-level operations"
+    )
+    linear_feature_request_project_id: str = Field(
+        default="",
+        description="Linear project ID where feature requests are tracked",
+    )
+    linear_feature_request_team_id: str = Field(
+        default="",
+        description="Linear team ID used when creating feature request issues",
+    )
     linear_client_id: str = Field(default="", description="Linear client ID")
     linear_client_secret: str = Field(default="", description="Linear client secret")
 

autogpt_platform/backend/migrations/20251126113000_add_llm_registry/migration.sql

@@ -1,81 +0,0 @@
--- 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 DEFAULT CURRENT_TIMESTAMP,
-    "name" TEXT NOT NULL,
-    "displayName" TEXT NOT NULL,
-    "description" TEXT,
-    "defaultCredentialProvider" TEXT,
-    "defaultCredentialId" TEXT,
-    "defaultCredentialType" TEXT,
-    "supportsTools" BOOLEAN NOT NULL DEFAULT TRUE,
-    "supportsJsonOutput" BOOLEAN NOT NULL DEFAULT TRUE,
-    "supportsReasoning" BOOLEAN NOT NULL DEFAULT FALSE,
-    "supportsParallelTool" BOOLEAN NOT NULL DEFAULT FALSE,
-    "metadata" JSONB NOT NULL DEFAULT '{}'::jsonb,
-
-    CONSTRAINT "LlmProvider_pkey" PRIMARY KEY ("id"),
-    CONSTRAINT "LlmProvider_name_key" UNIQUE ("name")
-);
-
--- CreateTable
-CREATE TABLE "LlmModel" (
-    "id" TEXT NOT NULL,
-    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
-    "updatedAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
-    "slug" TEXT NOT NULL,
-    "displayName" TEXT NOT NULL,
-    "description" TEXT,
-    "providerId" TEXT NOT NULL,
-    "contextWindow" INTEGER NOT NULL,
-    "maxOutputTokens" INTEGER,
-    "isEnabled" BOOLEAN NOT NULL DEFAULT TRUE,
-    "capabilities" JSONB NOT NULL DEFAULT '{}'::jsonb,
-    "metadata" JSONB NOT NULL DEFAULT '{}'::jsonb,
-
-    CONSTRAINT "LlmModel_pkey" PRIMARY KEY ("id"),
-    CONSTRAINT "LlmModel_slug_key" UNIQUE ("slug")
-);
-
--- CreateTable
-CREATE TABLE "LlmModelCost" (
-    "id" TEXT NOT NULL,
-    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
-    "updatedAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
-    "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 '{}'::jsonb,
-    "llmModelId" TEXT NOT NULL,
-
-    CONSTRAINT "LlmModelCost_pkey" PRIMARY KEY ("id")
-);
-
--- CreateIndex
-CREATE INDEX "LlmModel_providerId_isEnabled_idx" ON "LlmModel"("providerId", "isEnabled");
-
--- CreateIndex
-CREATE INDEX "LlmModel_slug_idx" ON "LlmModel"("slug");
-
--- CreateIndex
-CREATE INDEX "LlmModelCost_llmModelId_idx" ON "LlmModelCost"("llmModelId");
-
--- CreateIndex
-CREATE INDEX "LlmModelCost_credentialProvider_idx" ON "LlmModelCost"("credentialProvider");
-
--- CreateIndex
-CREATE UNIQUE INDEX "LlmModelCost_llmModelId_credentialProvider_unit_key" ON "LlmModelCost"("llmModelId", "credentialProvider", "unit");
-
--- AddForeignKey
-ALTER TABLE "LlmModel" ADD CONSTRAINT "LlmModel_providerId_fkey" FOREIGN KEY ("providerId") REFERENCES "LlmProvider"("id") ON DELETE RESTRICT ON UPDATE CASCADE;
-
--- AddForeignKey
-ALTER TABLE "LlmModelCost" ADD CONSTRAINT "LlmModelCost_llmModelId_fkey" FOREIGN KEY ("llmModelId") REFERENCES "LlmModel"("id") ON DELETE CASCADE ON UPDATE CASCADE;
-

autogpt_platform/backend/migrations/20251126120000_seed_llm_registry/migration.sql

@@ -1,226 +0,0 @@
--- Seed LLM Registry from existing hard-coded data
--- This migration populates the LlmProvider, LlmModel, and LlmModelCost tables
--- with data from the existing MODEL_METADATA and MODEL_COST dictionaries
-
--- Insert Providers
-INSERT INTO "LlmProvider" ("id", "name", "displayName", "description", "defaultCredentialProvider", "defaultCredentialType", "supportsTools", "supportsJsonOutput", "supportsReasoning", "supportsParallelTool", "metadata")
-VALUES
-    (gen_random_uuid(), 'openai', 'OpenAI', 'OpenAI language models', 'openai', 'api_key', true, true, true, true, '{}'::jsonb),
-    (gen_random_uuid(), 'anthropic', 'Anthropic', 'Anthropic Claude models', 'anthropic', 'api_key', true, true, true, false, '{}'::jsonb),
-    (gen_random_uuid(), 'groq', 'Groq', 'Groq inference API', 'groq', 'api_key', false, true, false, false, '{}'::jsonb),
-    (gen_random_uuid(), 'open_router', 'OpenRouter', 'OpenRouter unified API', 'open_router', 'api_key', true, true, false, false, '{}'::jsonb),
-    (gen_random_uuid(), 'aiml_api', 'AI/ML API', 'AI/ML API models', 'aiml_api', 'api_key', false, true, false, false, '{}'::jsonb),
-    (gen_random_uuid(), 'ollama', 'Ollama', 'Ollama local models', 'ollama', 'api_key', false, true, false, false, '{}'::jsonb),
-    (gen_random_uuid(), 'llama_api', 'Llama API', 'Llama API models', 'llama_api', 'api_key', false, true, false, false, '{}'::jsonb),
-    (gen_random_uuid(), 'v0', 'v0', 'v0 by Vercel models', 'v0', 'api_key', true, true, false, false, '{}'::jsonb)
-ON CONFLICT ("name") DO NOTHING;
-
--- Insert Models (using CTEs to reference provider IDs)
-WITH provider_ids AS (
-    SELECT "id", "name" FROM "LlmProvider"
-)
-INSERT INTO "LlmModel" ("id", "slug", "displayName", "description", "providerId", "contextWindow", "maxOutputTokens", "isEnabled", "capabilities", "metadata")
-SELECT
-    gen_random_uuid(),
-    model_slug,
-    model_display_name,
-    NULL,
-    p."id",
-    context_window,
-    max_output_tokens,
-    true,
-    '{}'::jsonb,
-    '{}'::jsonb
-FROM (VALUES
-    -- OpenAI models
-    ('o3', 'O3', 'openai', 200000, 100000),
-    ('o3-mini', 'O3 Mini', 'openai', 200000, 100000),
-    ('o1', 'O1', 'openai', 200000, 100000),
-    ('o1-mini', 'O1 Mini', 'openai', 128000, 65536),
-    ('gpt-5-2025-08-07', 'GPT 5', 'openai', 400000, 128000),
-    ('gpt-5.1-2025-11-13', 'GPT 5.1', 'openai', 400000, 128000),
-    ('gpt-5-mini-2025-08-07', 'GPT 5 Mini', 'openai', 400000, 128000),
-    ('gpt-5-nano-2025-08-07', 'GPT 5 Nano', 'openai', 400000, 128000),
-    ('gpt-5-chat-latest', 'GPT 5 Chat', 'openai', 400000, 16384),
-    ('gpt-4.1-2025-04-14', 'GPT 4.1', 'openai', 1000000, 32768),
-    ('gpt-4.1-mini-2025-04-14', 'GPT 4.1 Mini', 'openai', 1047576, 32768),
-    ('gpt-4o-mini', 'GPT 4o Mini', 'openai', 128000, 16384),
-    ('gpt-4o', 'GPT 4o', 'openai', 128000, 16384),
-    ('gpt-4-turbo', 'GPT 4 Turbo', 'openai', 128000, 4096),
-    ('gpt-3.5-turbo', 'GPT 3.5 Turbo', 'openai', 16385, 4096),
-    -- Anthropic models
-    ('claude-opus-4-1-20250805', 'Claude 4.1 Opus', 'anthropic', 200000, 32000),
-    ('claude-opus-4-20250514', 'Claude 4 Opus', 'anthropic', 200000, 32000),
-    ('claude-sonnet-4-20250514', 'Claude 4 Sonnet', 'anthropic', 200000, 64000),
-    ('claude-opus-4-5-20251101', 'Claude 4.5 Opus', 'anthropic', 200000, 64000),
-    ('claude-sonnet-4-5-20250929', 'Claude 4.5 Sonnet', 'anthropic', 200000, 64000),
-    ('claude-haiku-4-5-20251001', 'Claude 4.5 Haiku', 'anthropic', 200000, 64000),
-    ('claude-3-7-sonnet-20250219', 'Claude 3.7 Sonnet', 'anthropic', 200000, 64000),
-    ('claude-3-haiku-20240307', 'Claude 3 Haiku', 'anthropic', 200000, 4096),
-    -- AI/ML API models
-    ('Qwen/Qwen2.5-72B-Instruct-Turbo', 'Qwen 2.5 72B', 'aiml_api', 32000, 8000),
-    ('nvidia/llama-3.1-nemotron-70b-instruct', 'Llama 3.1 Nemotron 70B', 'aiml_api', 128000, 40000),
-    ('meta-llama/Llama-3.3-70B-Instruct-Turbo', 'Llama 3.3 70B', 'aiml_api', 128000, NULL),
-    ('meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', 'Meta Llama 3.1 70B', 'aiml_api', 131000, 2000),
-    ('meta-llama/Llama-3.2-3B-Instruct-Turbo', 'Llama 3.2 3B', 'aiml_api', 128000, NULL),
-    -- Groq models
-    ('llama-3.3-70b-versatile', 'Llama 3.3 70B', 'groq', 128000, 32768),
-    ('llama-3.1-8b-instant', 'Llama 3.1 8B', 'groq', 128000, 8192),
-    -- Ollama models
-    ('llama3.3', 'Llama 3.3', 'ollama', 8192, NULL),
-    ('llama3.2', 'Llama 3.2', 'ollama', 8192, NULL),
-    ('llama3', 'Llama 3', 'ollama', 8192, NULL),
-    ('llama3.1:405b', 'Llama 3.1 405B', 'ollama', 8192, NULL),
-    ('dolphin-mistral:latest', 'Dolphin Mistral', 'ollama', 32768, NULL),
-    -- OpenRouter models
-    ('google/gemini-2.5-pro-preview-03-25', 'Gemini 2.5 Pro', 'open_router', 1050000, 8192),
-    ('google/gemini-3-pro-preview', 'Gemini 3 Pro Preview', 'open_router', 1048576, 65535),
-    ('google/gemini-2.5-flash', 'Gemini 2.5 Flash', 'open_router', 1048576, 65535),
-    ('google/gemini-2.0-flash-001', 'Gemini 2.0 Flash', 'open_router', 1048576, 8192),
-    ('google/gemini-2.5-flash-lite-preview-06-17', 'Gemini 2.5 Flash Lite Preview', 'open_router', 1048576, 65535),
-    ('google/gemini-2.0-flash-lite-001', 'Gemini 2.0 Flash Lite', 'open_router', 1048576, 8192),
-    ('mistralai/mistral-nemo', 'Mistral Nemo', 'open_router', 128000, 4096),
-    ('cohere/command-r-08-2024', 'Command R', 'open_router', 128000, 4096),
-    ('cohere/command-r-plus-08-2024', 'Command R Plus', 'open_router', 128000, 4096),
-    ('deepseek/deepseek-chat', 'DeepSeek Chat', 'open_router', 64000, 2048),
-    ('deepseek/deepseek-r1-0528', 'DeepSeek R1', 'open_router', 163840, 163840),
-    ('perplexity/sonar', 'Perplexity Sonar', 'open_router', 127000, 8000),
-    ('perplexity/sonar-pro', 'Perplexity Sonar Pro', 'open_router', 200000, 8000),
-    ('perplexity/sonar-deep-research', 'Perplexity Sonar Deep Research', 'open_router', 128000, 16000),
-    ('nousresearch/hermes-3-llama-3.1-405b', 'Hermes 3 Llama 3.1 405B', 'open_router', 131000, 4096),
-    ('nousresearch/hermes-3-llama-3.1-70b', 'Hermes 3 Llama 3.1 70B', 'open_router', 12288, 12288),
-    ('openai/gpt-oss-120b', 'GPT OSS 120B', 'open_router', 131072, 131072),
-    ('openai/gpt-oss-20b', 'GPT OSS 20B', 'open_router', 131072, 32768),
-    ('amazon/nova-lite-v1', 'Amazon Nova Lite', 'open_router', 300000, 5120),
-    ('amazon/nova-micro-v1', 'Amazon Nova Micro', 'open_router', 128000, 5120),
-    ('amazon/nova-pro-v1', 'Amazon Nova Pro', 'open_router', 300000, 5120),
-    ('microsoft/wizardlm-2-8x22b', 'WizardLM 2 8x22B', 'open_router', 65536, 4096),
-    ('gryphe/mythomax-l2-13b', 'MythoMax L2 13B', 'open_router', 4096, 4096),
-    ('meta-llama/llama-4-scout', 'Llama 4 Scout', 'open_router', 131072, 131072),
-    ('meta-llama/llama-4-maverick', 'Llama 4 Maverick', 'open_router', 1048576, 1000000),
-    ('x-ai/grok-4', 'Grok 4', 'open_router', 256000, 256000),
-    ('x-ai/grok-4-fast', 'Grok 4 Fast', 'open_router', 2000000, 30000),
-    ('x-ai/grok-4.1-fast', 'Grok 4.1 Fast', 'open_router', 2000000, 30000),
-    ('x-ai/grok-code-fast-1', 'Grok Code Fast 1', 'open_router', 256000, 10000),
-    ('moonshotai/kimi-k2', 'Kimi K2', 'open_router', 131000, 131000),
-    ('qwen/qwen3-235b-a22b-thinking-2507', 'Qwen 3 235B Thinking', 'open_router', 262144, 262144),
-    ('qwen/qwen3-coder', 'Qwen 3 Coder', 'open_router', 262144, 262144),
-    -- Llama API models
-    ('Llama-4-Scout-17B-16E-Instruct-FP8', 'Llama 4 Scout', 'llama_api', 128000, 4028),
-    ('Llama-4-Maverick-17B-128E-Instruct-FP8', 'Llama 4 Maverick', 'llama_api', 128000, 4028),
-    ('Llama-3.3-8B-Instruct', 'Llama 3.3 8B', 'llama_api', 128000, 4028),
-    ('Llama-3.3-70B-Instruct', 'Llama 3.3 70B', 'llama_api', 128000, 4028),
-    -- v0 models
-    ('v0-1.5-md', 'v0 1.5 MD', 'v0', 128000, 64000),
-    ('v0-1.5-lg', 'v0 1.5 LG', 'v0', 512000, 64000),
-    ('v0-1.0-md', 'v0 1.0 MD', 'v0', 128000, 64000)
-) AS models(model_slug, model_display_name, provider_name, context_window, max_output_tokens)
-JOIN provider_ids p ON p."name" = models.provider_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", "unit", "creditCost", "credentialProvider", "credentialId", "credentialType", "currency", "metadata", "llmModelId")
-SELECT
-    gen_random_uuid(),
-    'RUN'::"LlmCostUnit",
-    cost,
-    p."name",
-    NULL,
-    'api_key',
-    NULL,
-    '{}'::jsonb,
-    m."id"
-FROM (VALUES
-    -- OpenAI costs
-    ('o3', 4),
-    ('o3-mini', 2),
-    ('o1', 16),
-    ('o1-mini', 4),
-    ('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),
-    ('gpt-3.5-turbo', 1),
-    -- Anthropic costs
-    ('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-3-7-sonnet-20250219', 5),
-    ('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-3-pro-preview', 5),
-    ('mistralai/mistral-nemo', 1),
-    ('cohere/command-r-08-2024', 1),
-    ('cohere/command-r-plus-08-2024', 3),
-    ('deepseek/deepseek-chat', 2),
-    ('perplexity/sonar', 1),
-    ('perplexity/sonar-pro', 5),
-    ('perplexity/sonar-deep-research', 10),
-    ('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),
-    ('gryphe/mythomax-l2-13b', 1),
-    ('meta-llama/llama-4-scout', 1),
-    ('meta-llama/llama-4-maverick', 1),
-    ('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") DO NOTHING;
-

autogpt_platform/backend/migrations/20251218100000_add_llm_model_migration/migration.sql

@@ -1,25 +0,0 @@
--- 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 INDEX "LlmModelMigration_sourceModelSlug_idx" ON "LlmModelMigration"("sourceModelSlug");
-
--- CreateIndex
-CREATE INDEX "LlmModelMigration_targetModelSlug_idx" ON "LlmModelMigration"("targetModelSlug");
-
--- CreateIndex
-CREATE INDEX "LlmModelMigration_isReverted_idx" ON "LlmModelMigration"("isReverted");

autogpt_platform/backend/migrations/20251224100000_add_llm_model_creator/migration.sql

@@ -1,127 +0,0 @@
--- Add LlmModelCreator table
--- Creator represents who made/trained the model (e.g., OpenAI, Meta)
--- This is distinct from Provider who hosts/serves the model (e.g., OpenRouter)
-
--- Create the LlmModelCreator table
-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")
-);
-
--- Create unique index on name
-CREATE UNIQUE INDEX "LlmModelCreator_name_key" ON "LlmModelCreator"("name");
-
--- Add creatorId column to LlmModel
-ALTER TABLE "LlmModel" ADD COLUMN "creatorId" TEXT;
-
--- Add foreign key constraint
-ALTER TABLE "LlmModel" ADD CONSTRAINT "LlmModel_creatorId_fkey"
-    FOREIGN KEY ("creatorId") REFERENCES "LlmModelCreator"("id") ON DELETE SET NULL ON UPDATE CASCADE;
-
--- Create index on creatorId
-CREATE INDEX "LlmModel_creatorId_idx" ON "LlmModel"("creatorId");
-
--- Seed creators based on known model creators
-INSERT INTO "LlmModelCreator" ("id", "updatedAt", "name", "displayName", "description", "websiteUrl", "metadata")
-VALUES
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'openai', 'OpenAI', 'Creator of GPT models', 'https://openai.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'anthropic', 'Anthropic', 'Creator of Claude models', 'https://anthropic.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'meta', 'Meta', 'Creator of Llama models', 'https://ai.meta.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'google', 'Google', 'Creator of Gemini models', 'https://deepmind.google', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'mistral', 'Mistral AI', 'Creator of Mistral models', 'https://mistral.ai', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'cohere', 'Cohere', 'Creator of Command models', 'https://cohere.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'deepseek', 'DeepSeek', 'Creator of DeepSeek models', 'https://deepseek.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'perplexity', 'Perplexity AI', 'Creator of Sonar models', 'https://perplexity.ai', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'qwen', 'Qwen (Alibaba)', 'Creator of Qwen models', 'https://qwenlm.github.io', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'xai', 'xAI', 'Creator of Grok models', 'https://x.ai', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'amazon', 'Amazon', 'Creator of Nova models', 'https://aws.amazon.com/bedrock', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'microsoft', 'Microsoft', 'Creator of WizardLM models', 'https://microsoft.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'moonshot', 'Moonshot AI', 'Creator of Kimi models', 'https://moonshot.cn', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'nvidia', 'NVIDIA', 'Creator of Nemotron models', 'https://nvidia.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'nous_research', 'Nous Research', 'Creator of Hermes models', 'https://nousresearch.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'vercel', 'Vercel', 'Creator of v0 models', 'https://vercel.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'cognitive_computations', 'Cognitive Computations', 'Creator of Dolphin models', 'https://erichartford.com', '{}'),
-    (gen_random_uuid(), CURRENT_TIMESTAMP, 'gryphe', 'Gryphe', 'Creator of MythoMax models', 'https://huggingface.co/Gryphe', '{}')
-ON CONFLICT ("name") DO NOTHING;
-
--- Update existing models with their creators
--- OpenAI models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'openai')
-WHERE "slug" LIKE 'gpt-%' OR "slug" LIKE 'o1%' OR "slug" LIKE 'o3%' OR "slug" LIKE 'openai/%';
-
--- Anthropic models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'anthropic')
-WHERE "slug" LIKE 'claude-%';
-
--- Meta/Llama models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'meta')
-WHERE "slug" LIKE 'llama%' OR "slug" LIKE 'Llama%' OR "slug" LIKE 'meta-llama/%' OR "slug" LIKE '%/llama-%';
-
--- Google models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'google')
-WHERE "slug" LIKE 'google/%' OR "slug" LIKE 'gemini%';
-
--- Mistral models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'mistral')
-WHERE "slug" LIKE 'mistral%' OR "slug" LIKE 'mistralai/%';
-
--- Cohere models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'cohere')
-WHERE "slug" LIKE 'cohere/%' OR "slug" LIKE 'command-%';
-
--- DeepSeek models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'deepseek')
-WHERE "slug" LIKE 'deepseek/%' OR "slug" LIKE 'deepseek-%';
-
--- Perplexity models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'perplexity')
-WHERE "slug" LIKE 'perplexity/%' OR "slug" LIKE 'sonar%';
-
--- Qwen models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'qwen')
-WHERE "slug" LIKE 'Qwen/%' OR "slug" LIKE 'qwen/%';
-
--- xAI/Grok models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'xai')
-WHERE "slug" LIKE 'x-ai/%' OR "slug" LIKE 'grok%';
-
--- Amazon models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'amazon')
-WHERE "slug" LIKE 'amazon/%' OR "slug" LIKE 'nova-%';
-
--- Microsoft models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'microsoft')
-WHERE "slug" LIKE 'microsoft/%' OR "slug" LIKE 'wizardlm%';
-
--- Moonshot models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'moonshot')
-WHERE "slug" LIKE 'moonshotai/%' OR "slug" LIKE 'kimi%';
-
--- NVIDIA models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'nvidia')
-WHERE "slug" LIKE 'nvidia/%' OR "slug" LIKE '%nemotron%';
-
--- Nous Research models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'nous_research')
-WHERE "slug" LIKE 'nousresearch/%' OR "slug" LIKE 'hermes%';
-
--- Vercel/v0 models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'vercel')
-WHERE "slug" LIKE 'v0-%';
-
--- Dolphin models (Cognitive Computations / Eric Hartford)
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'cognitive_computations')
-WHERE "slug" LIKE 'dolphin-%';
-
--- Gryphe models
-UPDATE "LlmModel" SET "creatorId" = (SELECT "id" FROM "LlmModelCreator" WHERE "name" = 'gryphe')
-WHERE "slug" LIKE 'gryphe/%' OR "slug" LIKE 'mythomax%';

autogpt_platform/backend/migrations/20260105120000_add_agent_node_model_index/migration.sql

@@ -1,4 +0,0 @@
--- CreateIndex
--- Index for efficient LLM model lookups on AgentNode.constantInput->>'model'
--- This improves performance of model migration queries in the LLM registry
-CREATE INDEX "AgentNode_constantInput_model_idx" ON "AgentNode" ((("constantInput"->>'model')));

autogpt_platform/backend/migrations/20260106150000_add_gpt52_model/migration.sql

@@ -1,52 +0,0 @@
--- Add GPT-5.2 model and update O3 slug
--- This migration adds the new GPT-5.2 model added in dev branch
-
--- Update O3 slug to match dev branch format
-UPDATE "LlmModel"
-SET "slug" = 'o3-2025-04-16'
-WHERE "slug" = 'o3';
-
--- Update cost reference for O3 if needed
--- (costs are linked by model ID, so no update needed)
-
--- Add GPT-5.2 model
-WITH provider_id AS (
-    SELECT "id" FROM "LlmProvider" WHERE "name" = 'openai'
-)
-INSERT INTO "LlmModel" ("id", "slug", "displayName", "description", "providerId", "contextWindow", "maxOutputTokens", "isEnabled", "capabilities", "metadata")
-SELECT
-    gen_random_uuid(),
-    'gpt-5.2-2025-12-11',
-    'GPT 5.2',
-    'OpenAI GPT-5.2 model',
-    p."id",
-    400000,
-    128000,
-    true,
-    '{}'::jsonb,
-    '{}'::jsonb
-FROM provider_id p
-ON CONFLICT ("slug") DO NOTHING;
-
--- Add cost for GPT-5.2
-WITH model_id AS (
-    SELECT m."id", p."name" as provider_name
-    FROM "LlmModel" m
-    JOIN "LlmProvider" p ON p."id" = m."providerId"
-    WHERE m."slug" = 'gpt-5.2-2025-12-11'
-)
-INSERT INTO "LlmModelCost" ("id", "unit", "creditCost", "credentialProvider", "credentialId", "credentialType", "currency", "metadata", "llmModelId")
-SELECT
-    gen_random_uuid(),
-    'RUN'::"LlmCostUnit",
-    3,  -- Same cost tier as GPT-5.1
-    m.provider_name,
-    NULL,
-    'api_key',
-    NULL,
-    '{}'::jsonb,
-    m."id"
-FROM model_id m
-WHERE NOT EXISTS (
-    SELECT 1 FROM "LlmModelCost" c WHERE c."llmModelId" = m."id"
-);

autogpt_platform/backend/migrations/20260107100000_add_llm_recommended_model/migration.sql

@@ -1,11 +0,0 @@
--- Add isRecommended field to LlmModel table
--- This allows admins to mark a model as the recommended default
-
-ALTER TABLE "LlmModel" ADD COLUMN "isRecommended" BOOLEAN NOT NULL DEFAULT false;
-
--- Set gpt-4o-mini as the default recommended model (if it exists)
-UPDATE "LlmModel" SET "isRecommended" = true WHERE "slug" = 'gpt-4o-mini' AND "isEnabled" = true;
-
--- Create unique partial index to enforce only one recommended model at the database level
--- This prevents multiple rows from having isRecommended = true
-CREATE UNIQUE INDEX "LlmModel_single_recommended_idx" ON "LlmModel" ("isRecommended") WHERE "isRecommended" = true;

autogpt_platform/backend/migrations/20260122000000_add_llm_price_tier/migration.sql

@@ -1,61 +0,0 @@
--- Add new columns to LlmModel table for extended model metadata
--- These columns support the LLM Picker UI enhancements
-
--- Add priceTier column: 1=cheapest, 2=medium, 3=expensive
-ALTER TABLE "LlmModel" ADD COLUMN IF NOT EXISTS "priceTier" INTEGER NOT NULL DEFAULT 1;
-
--- Add creatorId column for model creator relationship (if not exists)
-ALTER TABLE "LlmModel" ADD COLUMN IF NOT EXISTS "creatorId" TEXT;
-
--- Add isRecommended column (if not exists)
-ALTER TABLE "LlmModel" ADD COLUMN IF NOT EXISTS "isRecommended" BOOLEAN NOT NULL DEFAULT FALSE;
-
--- Add index on creatorId if not exists
-CREATE INDEX IF NOT EXISTS "LlmModel_creatorId_idx" ON "LlmModel"("creatorId");
-
--- Add foreign key for creatorId if not exists
-DO $$
-BEGIN
-    IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'LlmModel_creatorId_fkey') THEN
-        -- Only add FK if LlmModelCreator table exists
-        IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'LlmModelCreator') THEN
-            ALTER TABLE "LlmModel" ADD CONSTRAINT "LlmModel_creatorId_fkey"
-            FOREIGN KEY ("creatorId") REFERENCES "LlmModelCreator"("id") ON DELETE SET NULL ON UPDATE CASCADE;
-        END IF;
-    END IF;
-END $$;
-
--- Update priceTier values for existing models based on original MODEL_METADATA
--- Tier 1 = cheapest, Tier 2 = medium, Tier 3 = expensive
-
--- OpenAI models
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" = 'o3';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'o3-mini';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" = 'o1';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" = 'o1-mini';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" = 'gpt-5.2';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" = 'gpt-5.1';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'gpt-5';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'gpt-5-mini';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'gpt-5-nano';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" = 'gpt-5-chat-latest';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" LIKE 'gpt-4.1%';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'gpt-4o-mini';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" = 'gpt-4o';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" = 'gpt-4-turbo';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'gpt-3.5-turbo';
-
--- Anthropic models
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" LIKE 'claude-opus%';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" LIKE 'claude-sonnet%';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" LIKE 'claude%-4-5-sonnet%';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" LIKE 'claude%-haiku%';
-UPDATE "LlmModel" SET "priceTier" = 1 WHERE "slug" = 'claude-3-haiku-20240307';
-
--- OpenRouter models - Pro/expensive tiers
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" LIKE 'google/gemini%-pro%';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" LIKE '%command-r-plus%';
-UPDATE "LlmModel" SET "priceTier" = 2 WHERE "slug" LIKE '%sonar-pro%';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" LIKE '%sonar-deep-research%';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" = 'x-ai/grok-4';
-UPDATE "LlmModel" SET "priceTier" = 3 WHERE "slug" LIKE '%qwen3-coder%';

autogpt_platform/backend/migrations/20260212000000_add_llm_migration_composite_index/migration.sql

@@ -1,6 +0,0 @@
--- Add composite index on LlmModelMigration for optimized active migration queries
--- This index improves performance when querying for non-reverted migrations by model slug
--- Used by the billing system to apply customCreditCost overrides
-
--- CreateIndex
-CREATE INDEX "LlmModelMigration_sourceModelSlug_isReverted_idx" ON "LlmModelMigration"("sourceModelSlug", "isReverted");

autogpt_platform/backend/migrations/20260212000001_sync_llm_models_with_dev/migration.sql

@@ -1,65 +0,0 @@
--- Sync LLM models with latest dev branch changes
--- This migration adds new models and removes deprecated ones
-
--- Remove models that were deleted from dev
-DELETE FROM "LlmModelCost" WHERE "llmModelId" IN (
-    SELECT "id" FROM "LlmModel" WHERE "slug" IN ('o3', 'o3-mini', 'claude-3-7-sonnet-20250219')
-);
-
-DELETE FROM "LlmModel" WHERE "slug" IN ('o3', 'o3-mini', 'claude-3-7-sonnet-20250219');
-
--- Add new models from dev
-WITH provider_ids AS (
-    SELECT "id", "name" FROM "LlmProvider"
-)
-INSERT INTO "LlmModel" ("id", "slug", "displayName", "description", "providerId", "contextWindow", "maxOutputTokens", "isEnabled", "capabilities", "metadata", "createdAt", "updatedAt")
-SELECT
-    gen_random_uuid(),
-    model_slug,
-    model_display_name,
-    NULL,
-    p."id",
-    context_window,
-    max_output_tokens,
-    true,
-    '{}'::jsonb,
-    '{}'::jsonb,
-    NOW(),
-    NOW()
-FROM (VALUES
-    -- New OpenAI model
-    ('gpt-5.2-2025-12-11', 'GPT 5.2', 'openai', 400000, 128000),
-    -- New Anthropic model
-    ('claude-opus-4-6', 'Claude 4.6 Opus', 'anthropic', 200000, 64000)
-) AS models(model_slug, model_display_name, provider_name, context_window, max_output_tokens)
-JOIN provider_ids p ON p."name" = models.provider_name
-ON CONFLICT ("slug") DO NOTHING;
-
--- Add costs for new models
-WITH model_ids AS (
-    SELECT "id", "slug", "providerId" FROM "LlmModel"
-),
-provider_ids AS (
-    SELECT "id", "name" FROM "LlmProvider"
-)
-INSERT INTO "LlmModelCost" ("id", "unit", "creditCost", "credentialProvider", "credentialId", "credentialType", "currency", "metadata", "llmModelId", "createdAt", "updatedAt")
-SELECT
-    gen_random_uuid(),
-    'RUN'::"LlmCostUnit",
-    cost,
-    p."name",
-    NULL,
-    'api_key',
-    NULL,
-    '{}'::jsonb,
-    m."id",
-    NOW(),
-    NOW()
-FROM (VALUES
-    -- New model costs (estimate based on similar models)
-    ('gpt-5.2-2025-12-11', 5),  -- Similar to GPT 5.1
-    ('claude-opus-4-6', 21)     -- Similar to other Opus 4.x models
-) 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") DO NOTHING;

autogpt_platform/backend/schema.prisma

@@ -1143,154 +1143,6 @@ enum APIKeyStatus {
 
 ////////////////////////////////////////////////////////////
 ////////////////////////////////////////////////////////////
-/////////////   LLM REGISTRY AND BILLING DATA   /////////////
-////////////////////////////////////////////////////////////
-////////////////////////////////////////////////////////////
-
-// LlmCostUnit: Defines how LLM MODEL costs are calculated (per run or per token).
-// This is distinct from BlockCostType (in backend/data/block.py) which defines
-// how BLOCK EXECUTION costs are calculated (per run, per byte, or per second).
-// LlmCostUnit is for pricing individual LLM model API calls in the registry,
-// while BlockCostType is for billing platform block executions.
-enum LlmCostUnit {
-  RUN
-  TOKENS
-}
-
-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 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?
-
-  supportsTools        Boolean @default(true)
-  supportsJsonOutput   Boolean @default(true)
-  supportsReasoning    Boolean @default(false)
-  supportsParallelTool Boolean @default(false)
-
-  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
-  isEnabled       Boolean @default(true)
-  isRecommended   Boolean @default(false)
-
-  capabilities Json @default("{}")
-  metadata     Json @default("{}")
-
-  Costs LlmModelCost[]
-
-  @@index([providerId, isEnabled])
-  @@index([creatorId])
-  @@index([slug])
-}
-
-model LlmModelCost {
-  id        String     @id @default(uuid())
-  createdAt DateTime   @default(now())
-  updatedAt DateTime   @updatedAt
-  unit      LlmCostUnit @default(RUN)
-
-  creditCost Int
-
-  credentialProvider String
-  credentialId       String?
-  credentialType     String?
-  currency           String?
-
-  metadata Json @default("{}")
-
-  llmModelId String
-  Model      LlmModel @relation(fields: [llmModelId], references: [id], onDelete: Cascade)
-
-  @@unique([llmModelId, credentialProvider, unit])
-  @@index([llmModelId])
-  @@index([credentialProvider])
-}
-
-// Tracks model migrations for revert capability
-// When a model is disabled with migration, we record which nodes were affected
-// so they can be reverted when the original model is back online
-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")
-
-  // 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
-
-  // 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.
-  customCreditCost Int?
-
-  // Revert tracking
-  isReverted Boolean   @default(false)
-  revertedAt DateTime?
-
-  @@index([sourceModelSlug])
-  @@index([targetModelSlug])
-  @@index([isReverted])
-  @@index([sourceModelSlug, isReverted]) // Composite index for active migration queries
-}
 //////////////   OAUTH PROVIDER TABLES    //////////////////
 ////////////////////////////////////////////////////////////
 ////////////////////////////////////////////////////////////

autogpt_platform/frontend/src/app/(platform)/admin/layout.tsx

@@ -1,8 +1,5 @@
-"use client";
-
 import { Sidebar } from "@/components/__legacy__/Sidebar";
 import { Users, DollarSign, UserSearch, FileText } from "lucide-react";
-import { Cpu } from "@phosphor-icons/react";
 
 import { IconSliders } from "@/components/__legacy__/ui/icons";
 
@@ -29,11 +26,6 @@ const sidebarLinkGroups = [
         href: "/admin/execution-analytics",
         icon: <FileText className="h-6 w-6" />,
       },
-      {
-        text: "LLM Registry",
-        href: "/admin/llms",
-        icon: <Cpu size={24} />,
-      },
       {
         text: "Admin User Management",
         href: "/admin/settings",

autogpt_platform/frontend/src/app/(platform)/admin/llms/actions.ts

@@ -1,493 +0,0 @@
-"use server";
-
-import { revalidatePath } from "next/cache";
-
-// Generated API functions
-import {
-  getV2ListLlmProviders,
-  postV2CreateLlmProvider,
-  patchV2UpdateLlmProvider,
-  deleteV2DeleteLlmProvider,
-  getV2ListLlmModels,
-  postV2CreateLlmModel,
-  patchV2UpdateLlmModel,
-  patchV2ToggleLlmModelAvailability,
-  deleteV2DeleteLlmModelAndMigrateWorkflows,
-  getV2GetModelUsageCount,
-  getV2ListModelMigrations,
-  postV2RevertAModelMigration,
-  getV2ListModelCreators,
-  postV2CreateModelCreator,
-  patchV2UpdateModelCreator,
-  deleteV2DeleteModelCreator,
-  postV2SetRecommendedModel,
-} from "@/app/api/__generated__/endpoints/admin/admin";
-
-// Generated types
-import type { LlmProvidersResponse } from "@/app/api/__generated__/models/llmProvidersResponse";
-import type { LlmModelsResponse } from "@/app/api/__generated__/models/llmModelsResponse";
-import type { UpsertLlmProviderRequest } from "@/app/api/__generated__/models/upsertLlmProviderRequest";
-import type { CreateLlmModelRequest } from "@/app/api/__generated__/models/createLlmModelRequest";
-import type { UpdateLlmModelRequest } from "@/app/api/__generated__/models/updateLlmModelRequest";
-import type { ToggleLlmModelRequest } from "@/app/api/__generated__/models/toggleLlmModelRequest";
-import type { LlmMigrationsResponse } from "@/app/api/__generated__/models/llmMigrationsResponse";
-import type { LlmCreatorsResponse } from "@/app/api/__generated__/models/llmCreatorsResponse";
-import type { UpsertLlmCreatorRequest } from "@/app/api/__generated__/models/upsertLlmCreatorRequest";
-import type { LlmModelUsageResponse } from "@/app/api/__generated__/models/llmModelUsageResponse";
-import { LlmCostUnit } from "@/app/api/__generated__/models/llmCostUnit";
-
-const ADMIN_LLM_PATH = "/admin/llms";
-
-// =============================================================================
-// Utilities
-// =============================================================================
-
-/**
- * Extracts and validates a required string field from FormData.
- * Throws an error if the field is missing or empty.
- */
-function getRequiredFormField(
-  formData: FormData,
-  fieldName: string,
-  displayName?: string,
-): string {
-  const raw = formData.get(fieldName);
-  const value = raw ? String(raw).trim() : "";
-  if (!value) {
-    throw new Error(`${displayName || fieldName} is required`);
-  }
-  return value;
-}
-
-/**
- * Extracts and validates a required positive number field from FormData.
- * Throws an error if the field is missing, empty, or not a positive number.
- */
-function getRequiredPositiveNumber(
-  formData: FormData,
-  fieldName: string,
-  displayName?: string,
-): number {
-  const raw = formData.get(fieldName);
-  const value = Number(raw);
-  if (raw === null || raw === "" || !Number.isFinite(value) || value <= 0) {
-    throw new Error(`${displayName || fieldName} must be a positive number`);
-  }
-  return value;
-}
-
-/**
- * Extracts and validates a required number field from FormData.
- * Throws an error if the field is missing, empty, or not a finite number.
- */
-function getRequiredNumber(
-  formData: FormData,
-  fieldName: string,
-  displayName?: string,
-): number {
-  const raw = formData.get(fieldName);
-  const value = Number(raw);
-  if (raw === null || raw === "" || !Number.isFinite(value)) {
-    throw new Error(`${displayName || fieldName} is required`);
-  }
-  return value;
-}
-
-// =============================================================================
-// Provider Actions
-// =============================================================================
-
-export async function fetchLlmProviders(): Promise<LlmProvidersResponse> {
-  const response = await getV2ListLlmProviders({ include_models: true });
-  if (response.status !== 200) {
-    throw new Error("Failed to fetch LLM providers");
-  }
-  return response.data;
-}
-
-export async function createLlmProviderAction(formData: FormData) {
-  const payload: UpsertLlmProviderRequest = {
-    name: String(formData.get("name") || "").trim(),
-    display_name: String(formData.get("display_name") || "").trim(),
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    default_credential_provider: formData.get("default_credential_provider")
-      ? String(formData.get("default_credential_provider")).trim()
-      : undefined,
-    default_credential_id: formData.get("default_credential_id")
-      ? String(formData.get("default_credential_id")).trim()
-      : undefined,
-    default_credential_type: formData.get("default_credential_type")
-      ? String(formData.get("default_credential_type")).trim()
-      : "api_key",
-    supports_tools: formData.getAll("supports_tools").includes("on"),
-    supports_json_output: formData
-      .getAll("supports_json_output")
-      .includes("on"),
-    supports_reasoning: formData.getAll("supports_reasoning").includes("on"),
-    supports_parallel_tool: formData
-      .getAll("supports_parallel_tool")
-      .includes("on"),
-    metadata: {},
-  };
-
-  const response = await postV2CreateLlmProvider(payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to create LLM provider");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function deleteLlmProviderAction(
-  formData: FormData,
-): Promise<void> {
-  const providerId = getRequiredFormField(
-    formData,
-    "provider_id",
-    "Provider id",
-  );
-
-  const response = await deleteV2DeleteLlmProvider(providerId);
-  if (response.status !== 200) {
-    const errorData = response.data as { detail?: string };
-    throw new Error(errorData?.detail || "Failed to delete provider");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function updateLlmProviderAction(formData: FormData) {
-  const providerId = getRequiredFormField(
-    formData,
-    "provider_id",
-    "Provider id",
-  );
-
-  const payload: UpsertLlmProviderRequest = {
-    name: String(formData.get("name") || "").trim(),
-    display_name: String(formData.get("display_name") || "").trim(),
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    default_credential_provider: formData.get("default_credential_provider")
-      ? String(formData.get("default_credential_provider")).trim()
-      : undefined,
-    default_credential_id: formData.get("default_credential_id")
-      ? String(formData.get("default_credential_id")).trim()
-      : undefined,
-    default_credential_type: formData.get("default_credential_type")
-      ? String(formData.get("default_credential_type")).trim()
-      : "api_key",
-    supports_tools: formData.getAll("supports_tools").includes("on"),
-    supports_json_output: formData
-      .getAll("supports_json_output")
-      .includes("on"),
-    supports_reasoning: formData.getAll("supports_reasoning").includes("on"),
-    supports_parallel_tool: formData
-      .getAll("supports_parallel_tool")
-      .includes("on"),
-    metadata: {},
-  };
-
-  const response = await patchV2UpdateLlmProvider(providerId, payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to update LLM provider");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-// =============================================================================
-// Model Actions
-// =============================================================================
-
-export async function fetchLlmModels(): Promise<LlmModelsResponse> {
-  const response = await getV2ListLlmModels();
-  if (response.status !== 200) {
-    throw new Error("Failed to fetch LLM models");
-  }
-  return response.data;
-}
-
-export async function createLlmModelAction(formData: FormData) {
-  const providerId = getRequiredFormField(formData, "provider_id", "Provider");
-  const creatorId = formData.get("creator_id");
-  const contextWindow = getRequiredPositiveNumber(
-    formData,
-    "context_window",
-    "Context window",
-  );
-  const creditCost = getRequiredNumber(formData, "credit_cost", "Credit cost");
-
-  // Fetch provider to get default credentials
-  const providersResponse = await getV2ListLlmProviders({
-    include_models: false,
-  });
-  if (providersResponse.status !== 200) {
-    throw new Error("Failed to fetch providers");
-  }
-  const provider = providersResponse.data.providers.find(
-    (p) => p.id === providerId,
-  );
-
-  if (!provider) {
-    throw new Error("Provider not found");
-  }
-
-  const payload: CreateLlmModelRequest = {
-    slug: String(formData.get("slug") || "").trim(),
-    display_name: String(formData.get("display_name") || "").trim(),
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    provider_id: providerId,
-    creator_id: creatorId ? String(creatorId) : undefined,
-    context_window: contextWindow,
-    max_output_tokens: formData.get("max_output_tokens")
-      ? Number(formData.get("max_output_tokens"))
-      : undefined,
-    is_enabled: formData.getAll("is_enabled").includes("on"),
-    capabilities: {},
-    metadata: {},
-    costs: [
-      {
-        unit: (formData.get("unit") as LlmCostUnit) || LlmCostUnit.RUN,
-        credit_cost: creditCost,
-        credential_provider:
-          provider.default_credential_provider || provider.name,
-        credential_id: provider.default_credential_id || undefined,
-        credential_type: provider.default_credential_type || "api_key",
-        metadata: {},
-      },
-    ],
-  };
-
-  const response = await postV2CreateLlmModel(payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to create LLM model");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function updateLlmModelAction(formData: FormData) {
-  const modelId = getRequiredFormField(formData, "model_id", "Model id");
-  const creatorId = formData.get("creator_id");
-
-  const payload: UpdateLlmModelRequest = {
-    display_name: formData.get("display_name")
-      ? String(formData.get("display_name"))
-      : undefined,
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    provider_id: formData.get("provider_id")
-      ? String(formData.get("provider_id"))
-      : undefined,
-    creator_id: creatorId ? String(creatorId) : undefined,
-    context_window: formData.get("context_window")
-      ? Number(formData.get("context_window"))
-      : undefined,
-    max_output_tokens: formData.get("max_output_tokens")
-      ? Number(formData.get("max_output_tokens"))
-      : undefined,
-    is_enabled: formData.has("is_enabled")
-      ? formData.getAll("is_enabled").includes("on")
-      : undefined,
-    costs: formData.get("credit_cost")
-      ? [
-          {
-            unit: (formData.get("unit") as LlmCostUnit) || LlmCostUnit.RUN,
-            credit_cost: Number(formData.get("credit_cost")),
-            credential_provider: String(
-              formData.get("credential_provider") || "",
-            ).trim(),
-            credential_id: formData.get("credential_id")
-              ? String(formData.get("credential_id"))
-              : undefined,
-            credential_type: formData.get("credential_type")
-              ? String(formData.get("credential_type"))
-              : undefined,
-            metadata: {},
-          },
-        ]
-      : undefined,
-  };
-
-  const response = await patchV2UpdateLlmModel(modelId, payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to update LLM model");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function toggleLlmModelAction(formData: FormData): Promise<void> {
-  const modelId = getRequiredFormField(formData, "model_id", "Model id");
-  const shouldEnable = formData.get("is_enabled") === "true";
-  const migrateToSlug = formData.get("migrate_to_slug");
-  const migrationReason = formData.get("migration_reason");
-  const customCreditCost = formData.get("custom_credit_cost");
-
-  const payload: ToggleLlmModelRequest = {
-    is_enabled: shouldEnable,
-    migrate_to_slug: migrateToSlug ? String(migrateToSlug) : undefined,
-    migration_reason: migrationReason ? String(migrationReason) : undefined,
-    custom_credit_cost: customCreditCost ? Number(customCreditCost) : undefined,
-  };
-
-  const response = await patchV2ToggleLlmModelAvailability(modelId, payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to toggle LLM model");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function deleteLlmModelAction(formData: FormData): Promise<void> {
-  const modelId = getRequiredFormField(formData, "model_id", "Model id");
-  const rawReplacement = formData.get("replacement_model_slug");
-  const replacementModelSlug =
-    rawReplacement && String(rawReplacement).trim()
-      ? String(rawReplacement).trim()
-      : undefined;
-
-  const response = await deleteV2DeleteLlmModelAndMigrateWorkflows(modelId, {
-    replacement_model_slug: replacementModelSlug,
-  });
-  if (response.status !== 200) {
-    throw new Error("Failed to delete model");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function fetchLlmModelUsage(
-  modelId: string,
-): Promise<LlmModelUsageResponse> {
-  const response = await getV2GetModelUsageCount(modelId);
-  if (response.status !== 200) {
-    throw new Error("Failed to fetch model usage");
-  }
-  return response.data;
-}
-
-// =============================================================================
-// Migration Actions
-// =============================================================================
-
-export async function fetchLlmMigrations(
-  includeReverted: boolean = false,
-): Promise<LlmMigrationsResponse> {
-  const response = await getV2ListModelMigrations({
-    include_reverted: includeReverted,
-  });
-  if (response.status !== 200) {
-    throw new Error("Failed to fetch migrations");
-  }
-  return response.data;
-}
-
-export async function revertLlmMigrationAction(
-  formData: FormData,
-): Promise<void> {
-  const migrationId = getRequiredFormField(
-    formData,
-    "migration_id",
-    "Migration id",
-  );
-
-  const response = await postV2RevertAModelMigration(migrationId, null);
-  if (response.status !== 200) {
-    throw new Error("Failed to revert migration");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-// =============================================================================
-// Creator Actions
-// =============================================================================
-
-export async function fetchLlmCreators(): Promise<LlmCreatorsResponse> {
-  const response = await getV2ListModelCreators();
-  if (response.status !== 200) {
-    throw new Error("Failed to fetch creators");
-  }
-  return response.data;
-}
-
-export async function createLlmCreatorAction(
-  formData: FormData,
-): Promise<void> {
-  const payload: UpsertLlmCreatorRequest = {
-    name: String(formData.get("name") || "").trim(),
-    display_name: String(formData.get("display_name") || "").trim(),
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    website_url: formData.get("website_url")
-      ? String(formData.get("website_url")).trim()
-      : undefined,
-    logo_url: formData.get("logo_url")
-      ? String(formData.get("logo_url")).trim()
-      : undefined,
-    metadata: {},
-  };
-
-  const response = await postV2CreateModelCreator(payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to create creator");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function updateLlmCreatorAction(
-  formData: FormData,
-): Promise<void> {
-  const creatorId = getRequiredFormField(formData, "creator_id", "Creator id");
-
-  const payload: UpsertLlmCreatorRequest = {
-    name: String(formData.get("name") || "").trim(),
-    display_name: String(formData.get("display_name") || "").trim(),
-    description: formData.get("description")
-      ? String(formData.get("description"))
-      : undefined,
-    website_url: formData.get("website_url")
-      ? String(formData.get("website_url")).trim()
-      : undefined,
-    logo_url: formData.get("logo_url")
-      ? String(formData.get("logo_url")).trim()
-      : undefined,
-    metadata: {},
-  };
-
-  const response = await patchV2UpdateModelCreator(creatorId, payload);
-  if (response.status !== 200) {
-    throw new Error("Failed to update creator");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-export async function deleteLlmCreatorAction(
-  formData: FormData,
-): Promise<void> {
-  const creatorId = getRequiredFormField(formData, "creator_id", "Creator id");
-
-  const response = await deleteV2DeleteModelCreator(creatorId);
-  if (response.status !== 200) {
-    throw new Error("Failed to delete creator");
-  }
-  revalidatePath(ADMIN_LLM_PATH);
-}
-
-// =============================================================================
-// Recommended Model Actions
-// =============================================================================
-
-export async function setRecommendedModelAction(
-  formData: FormData,
-): Promise<void> {
-  const modelId = getRequiredFormField(formData, "model_id", "Model id");
-
-  const response = await postV2SetRecommendedModel({ model_id: modelId });
-  if (response.status !== 200) {
-    throw new Error("Failed to set recommended model");
-  }
-
-  revalidatePath(ADMIN_LLM_PATH);
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/AddCreatorModal.tsx

@@ -1,147 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import { createLlmCreatorAction } from "../actions";
-import { useRouter } from "next/navigation";
-
-export function AddCreatorModal() {
-  const [open, setOpen] = useState(false);
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await createLlmCreatorAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to create creator");
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Add Creator"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "512px" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="primary" size="small">
-          Add Creator
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Add a new model creator (the organization that made/trained the
-          model).
-        </div>
-
-        <form action={handleSubmit} className="space-y-4">
-          <div className="grid gap-4 sm:grid-cols-2">
-            <div className="space-y-2">
-              <label
-                htmlFor="name"
-                className="text-sm font-medium text-foreground"
-              >
-                Name (slug) <span className="text-destructive">*</span>
-              </label>
-              <input
-                id="name"
-                required
-                name="name"
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="openai"
-              />
-              <p className="text-xs text-muted-foreground">
-                Lowercase identifier (e.g., openai, meta, anthropic)
-              </p>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="display_name"
-                className="text-sm font-medium text-foreground"
-              >
-                Display Name <span className="text-destructive">*</span>
-              </label>
-              <input
-                id="display_name"
-                required
-                name="display_name"
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="OpenAI"
-              />
-            </div>
-          </div>
-
-          <div className="space-y-2">
-            <label
-              htmlFor="description"
-              className="text-sm font-medium text-foreground"
-            >
-              Description
-            </label>
-            <textarea
-              id="description"
-              name="description"
-              rows={2}
-              className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-              placeholder="Creator of GPT models..."
-            />
-          </div>
-
-          <div className="space-y-2">
-            <label
-              htmlFor="website_url"
-              className="text-sm font-medium text-foreground"
-            >
-              Website URL
-            </label>
-            <input
-              id="website_url"
-              name="website_url"
-              type="url"
-              className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-              placeholder="https://openai.com"
-            />
-          </div>
-
-          {error && (
-            <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-              {error}
-            </div>
-          )}
-
-          <Dialog.Footer>
-            <Button
-              variant="ghost"
-              size="small"
-              type="button"
-              onClick={() => {
-                setOpen(false);
-                setError(null);
-              }}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Creating..." : "Add Creator"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/AddModelModal.tsx

@@ -1,314 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import { createLlmModelAction } from "../actions";
-import { useRouter } from "next/navigation";
-
-interface Props {
-  providers: LlmProvider[];
-  creators: LlmModelCreator[];
-}
-
-export function AddModelModal({ providers, creators }: Props) {
-  const [open, setOpen] = useState(false);
-  const [selectedCreatorId, setSelectedCreatorId] = useState("");
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await createLlmModelAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to create model");
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  // When provider changes, auto-select matching creator if one exists
-  function handleProviderChange(providerId: string) {
-    const provider = providers.find((p) => p.id === providerId);
-    if (provider) {
-      // Find creator with same name as provider (e.g., "openai" -> "openai")
-      const matchingCreator = creators.find((c) => c.name === provider.name);
-      if (matchingCreator) {
-        setSelectedCreatorId(matchingCreator.id);
-      } else {
-        // No matching creator (e.g., OpenRouter hosts other creators' models)
-        setSelectedCreatorId("");
-      }
-    }
-  }
-
-  return (
-    <Dialog
-      title="Add Model"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "768px", maxHeight: "90vh", overflowY: "auto" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="primary" size="small">
-          Add Model
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Register a new model slug, metadata, and pricing.
-        </div>
-
-        <form action={handleSubmit} className="space-y-6">
-          {/* Basic Information */}
-          <div className="space-y-4">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Basic Information
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Core model details
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="slug"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Model Slug <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="slug"
-                  required
-                  name="slug"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="gpt-4.1-mini-2025-04-14"
-                />
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="display_name"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Display Name <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="display_name"
-                  required
-                  name="display_name"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="GPT 4.1 Mini"
-                />
-              </div>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="description"
-                className="text-sm font-medium text-foreground"
-              >
-                Description
-              </label>
-              <textarea
-                id="description"
-                name="description"
-                rows={3}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="Optional description..."
-              />
-            </div>
-          </div>
-
-          {/* Model Configuration */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Model Configuration
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Model capabilities and limits
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="provider_id"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Provider <span className="text-destructive">*</span>
-                </label>
-                <select
-                  id="provider_id"
-                  required
-                  name="provider_id"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  defaultValue=""
-                  onChange={(e) => handleProviderChange(e.target.value)}
-                >
-                  <option value="" disabled>
-                    Select provider
-                  </option>
-                  {providers.map((provider) => (
-                    <option key={provider.id} value={provider.id}>
-                      {provider.display_name} ({provider.name})
-                    </option>
-                  ))}
-                </select>
-                <p className="text-xs text-muted-foreground">
-                  Who hosts/serves the model
-                </p>
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="creator_id"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Creator
-                </label>
-                <select
-                  id="creator_id"
-                  name="creator_id"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  value={selectedCreatorId}
-                  onChange={(e) => setSelectedCreatorId(e.target.value)}
-                >
-                  <option value="">No creator selected</option>
-                  {creators.map((creator) => (
-                    <option key={creator.id} value={creator.id}>
-                      {creator.display_name} ({creator.name})
-                    </option>
-                  ))}
-                </select>
-                <p className="text-xs text-muted-foreground">
-                  Who made/trained the model (e.g., OpenAI, Meta)
-                </p>
-              </div>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="context_window"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Context Window <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="context_window"
-                  required
-                  type="number"
-                  name="context_window"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="128000"
-                  min={1}
-                />
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="max_output_tokens"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Max Output Tokens
-                </label>
-                <input
-                  id="max_output_tokens"
-                  type="number"
-                  name="max_output_tokens"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="16384"
-                  min={1}
-                />
-              </div>
-            </div>
-          </div>
-
-          {/* Pricing */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">Pricing</h3>
-              <p className="text-xs text-muted-foreground">
-                Credit cost per run (credentials are managed via the provider)
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-1">
-              <div className="space-y-2">
-                <label
-                  htmlFor="credit_cost"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Credit Cost <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="credit_cost"
-                  required
-                  type="number"
-                  name="credit_cost"
-                  step="1"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="5"
-                  min={0}
-                />
-              </div>
-            </div>
-            <p className="text-xs text-muted-foreground">
-              Credit cost is always in platform credits. Credentials are
-              inherited from the selected provider.
-            </p>
-          </div>
-
-          {/* Enabled Toggle */}
-          <div className="flex items-center gap-3 border-t border-border pt-6">
-            <input type="hidden" name="is_enabled" value="off" />
-            <input
-              id="is_enabled"
-              type="checkbox"
-              name="is_enabled"
-              defaultChecked
-              className="h-4 w-4 rounded border-input"
-            />
-            <label
-              htmlFor="is_enabled"
-              className="text-sm font-medium text-foreground"
-            >
-              Enabled by default
-            </label>
-          </div>
-
-          {error && (
-            <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-              {error}
-            </div>
-          )}
-
-          <Dialog.Footer>
-            <Button
-              variant="ghost"
-              size="small"
-              type="button"
-              onClick={() => {
-                setOpen(false);
-                setError(null);
-              }}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Creating..." : "Save Model"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/AddProviderModal.tsx

@@ -1,268 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import { createLlmProviderAction } from "../actions";
-import { useRouter } from "next/navigation";
-
-export function AddProviderModal() {
-  const [open, setOpen] = useState(false);
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await createLlmProviderAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(
-        err instanceof Error ? err.message : "Failed to create provider",
-      );
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Add Provider"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "768px", maxHeight: "90vh", overflowY: "auto" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="primary" size="small">
-          Add Provider
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Define a new upstream provider and default credential information.
-        </div>
-
-        {/* Setup Instructions */}
-        <div className="mb-6 rounded-lg border border-primary/30 bg-primary/5 p-4">
-          <div className="space-y-2">
-            <h4 className="text-sm font-semibold text-foreground">
-              Before Adding a Provider
-            </h4>
-            <p className="text-xs text-muted-foreground">
-              To use a new provider, you must first configure its credentials in
-              the backend:
-            </p>
-            <ol className="list-inside list-decimal space-y-1 text-xs text-muted-foreground">
-              <li>
-                Add the credential to{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono">
-                  backend/integrations/credentials_store.py
-                </code>{" "}
-                with a UUID, provider name, and settings secret reference
-              </li>
-              <li>
-                Add it to the{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono">
-                  PROVIDER_CREDENTIALS
-                </code>{" "}
-                dictionary in{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono">
-                  backend/data/block_cost_config.py
-                </code>
-              </li>
-              <li>
-                Use the <strong>same provider name</strong> in the
-                &quot;Credential Provider&quot; field below that matches the key
-                in{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono">
-                  PROVIDER_CREDENTIALS
-                </code>
-              </li>
-            </ol>
-          </div>
-        </div>
-
-        <form action={handleSubmit} className="space-y-6">
-          {/* Basic Information */}
-          <div className="space-y-4">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Basic Information
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Core provider details
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="name"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Provider Slug <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="name"
-                  required
-                  name="name"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="e.g. openai"
-                />
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="display_name"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Display Name <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="display_name"
-                  required
-                  name="display_name"
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="OpenAI"
-                />
-              </div>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="description"
-                className="text-sm font-medium text-foreground"
-              >
-                Description
-              </label>
-              <textarea
-                id="description"
-                name="description"
-                rows={3}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="Optional description..."
-              />
-            </div>
-          </div>
-
-          {/* Default Credentials */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Default Credentials
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Credential provider name that matches the key in{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono text-xs">
-                  PROVIDER_CREDENTIALS
-                </code>
-              </p>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="default_credential_provider"
-                className="text-sm font-medium text-foreground"
-              >
-                Credential Provider <span className="text-destructive">*</span>
-              </label>
-              <input
-                id="default_credential_provider"
-                name="default_credential_provider"
-                required
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="openai"
-              />
-              <p className="text-xs text-muted-foreground">
-                <strong>Important:</strong> This must exactly match the key in
-                the{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono text-xs">
-                  PROVIDER_CREDENTIALS
-                </code>{" "}
-                dictionary in{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono text-xs">
-                  block_cost_config.py
-                </code>
-                . Common values: &quot;openai&quot;, &quot;anthropic&quot;,
-                &quot;groq&quot;, &quot;open_router&quot;, etc.
-              </p>
-            </div>
-          </div>
-
-          {/* Capabilities */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Capabilities
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Provider feature flags
-              </p>
-            </div>
-            <div className="grid gap-3 sm:grid-cols-2">
-              {[
-                { name: "supports_tools", label: "Supports tools" },
-                { name: "supports_json_output", label: "Supports JSON output" },
-                { name: "supports_reasoning", label: "Supports reasoning" },
-                {
-                  name: "supports_parallel_tool",
-                  label: "Supports parallel tool calls",
-                },
-              ].map(({ name, label }) => (
-                <div
-                  key={name}
-                  className="flex items-center gap-3 rounded-md border border-border bg-muted/30 px-4 py-3 transition-colors hover:bg-muted/50"
-                >
-                  <input type="hidden" name={name} value="off" />
-                  <input
-                    id={name}
-                    type="checkbox"
-                    name={name}
-                    defaultChecked={
-                      name !== "supports_reasoning" &&
-                      name !== "supports_parallel_tool"
-                    }
-                    className="h-4 w-4 rounded border-input"
-                  />
-                  <label
-                    htmlFor={name}
-                    className="text-sm font-medium text-foreground"
-                  >
-                    {label}
-                  </label>
-                </div>
-              ))}
-            </div>
-          </div>
-
-          {error && (
-            <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-              {error}
-            </div>
-          )}
-
-          <Dialog.Footer>
-            <Button
-              variant="ghost"
-              size="small"
-              type="button"
-              onClick={() => {
-                setOpen(false);
-                setError(null);
-              }}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Creating..." : "Save Provider"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/CreatorsTable.tsx

@@ -1,195 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import {
-  Table,
-  TableBody,
-  TableCell,
-  TableHead,
-  TableHeader,
-  TableRow,
-} from "@/components/atoms/Table/Table";
-import { Button } from "@/components/atoms/Button/Button";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { updateLlmCreatorAction } from "../actions";
-import { useRouter } from "next/navigation";
-import { DeleteCreatorModal } from "./DeleteCreatorModal";
-
-export function CreatorsTable({ creators }: { creators: LlmModelCreator[] }) {
-  if (!creators.length) {
-    return (
-      <div className="rounded-lg border border-dashed border-border p-6 text-center text-sm text-muted-foreground">
-        No creators registered yet.
-      </div>
-    );
-  }
-
-  return (
-    <div className="rounded-lg border">
-      <Table>
-        <TableHeader>
-          <TableRow>
-            <TableHead>Creator</TableHead>
-            <TableHead>Description</TableHead>
-            <TableHead>Website</TableHead>
-            <TableHead>Actions</TableHead>
-          </TableRow>
-        </TableHeader>
-        <TableBody>
-          {creators.map((creator) => (
-            <TableRow key={creator.id}>
-              <TableCell>
-                <div className="font-medium">{creator.display_name}</div>
-                <div className="text-xs text-muted-foreground">
-                  {creator.name}
-                </div>
-              </TableCell>
-              <TableCell>
-                <span className="text-sm text-muted-foreground">
-                  {creator.description || "—"}
-                </span>
-              </TableCell>
-              <TableCell>
-                {creator.website_url ? (
-                  <a
-                    href={creator.website_url}
-                    target="_blank"
-                    rel="noopener noreferrer"
-                    className="text-sm text-primary hover:underline"
-                  >
-                    {(() => {
-                      try {
-                        return new URL(creator.website_url).hostname;
-                      } catch {
-                        return creator.website_url;
-                      }
-                    })()}
-                  </a>
-                ) : (
-                  <span className="text-muted-foreground">—</span>
-                )}
-              </TableCell>
-              <TableCell>
-                <div className="flex items-center justify-end gap-2">
-                  <EditCreatorModal creator={creator} />
-                  <DeleteCreatorModal creator={creator} />
-                </div>
-              </TableCell>
-            </TableRow>
-          ))}
-        </TableBody>
-      </Table>
-    </div>
-  );
-}
-
-function EditCreatorModal({ creator }: { creator: LlmModelCreator }) {
-  const [open, setOpen] = useState(false);
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await updateLlmCreatorAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to update creator");
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Edit Creator"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "512px" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="outline" size="small" className="min-w-0">
-          Edit
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <form action={handleSubmit} className="space-y-4">
-          <input type="hidden" name="creator_id" value={creator.id} />
-
-          <div className="grid gap-4 sm:grid-cols-2">
-            <div className="space-y-2">
-              <label className="text-sm font-medium">Name (slug)</label>
-              <input
-                required
-                name="name"
-                defaultValue={creator.name}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm"
-              />
-            </div>
-            <div className="space-y-2">
-              <label className="text-sm font-medium">Display Name</label>
-              <input
-                required
-                name="display_name"
-                defaultValue={creator.display_name}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm"
-              />
-            </div>
-          </div>
-
-          <div className="space-y-2">
-            <label className="text-sm font-medium">Description</label>
-            <textarea
-              name="description"
-              rows={2}
-              defaultValue={creator.description ?? ""}
-              className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm"
-            />
-          </div>
-
-          <div className="space-y-2">
-            <label className="text-sm font-medium">Website URL</label>
-            <input
-              name="website_url"
-              type="url"
-              defaultValue={creator.website_url ?? ""}
-              className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm"
-            />
-          </div>
-
-          {error && (
-            <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-              {error}
-            </div>
-          )}
-
-          <Dialog.Footer>
-            <Button
-              variant="ghost"
-              size="small"
-              type="button"
-              onClick={() => {
-                setOpen(false);
-                setError(null);
-              }}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Updating..." : "Update"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/DeleteCreatorModal.tsx

@@ -1,107 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { useRouter } from "next/navigation";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import { deleteLlmCreatorAction } from "../actions";
-
-export function DeleteCreatorModal({ creator }: { creator: LlmModelCreator }) {
-  const [open, setOpen] = useState(false);
-  const [isDeleting, setIsDeleting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleDelete(formData: FormData) {
-    setIsDeleting(true);
-    setError(null);
-    try {
-      await deleteLlmCreatorAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to delete creator");
-    } finally {
-      setIsDeleting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Delete Creator"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "480px" }}
-    >
-      <Dialog.Trigger>
-        <Button
-          type="button"
-          variant="outline"
-          size="small"
-          className="min-w-0 text-destructive hover:bg-destructive/10"
-        >
-          Delete
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="space-y-4">
-          <div className="rounded-lg border border-amber-500/30 bg-amber-500/10 p-4 dark:border-amber-400/30 dark:bg-amber-400/10">
-            <div className="flex items-start gap-3">
-              <div className="flex-shrink-0 text-amber-600 dark:text-amber-400">
-                ⚠️
-              </div>
-              <div className="text-sm text-foreground">
-                <p className="font-semibold">You are about to delete:</p>
-                <p className="mt-1">
-                  <span className="font-medium">{creator.display_name}</span>{" "}
-                  <span className="text-muted-foreground">
-                    ({creator.name})
-                  </span>
-                </p>
-                <p className="mt-2 text-muted-foreground">
-                  Models using this creator will have their creator field
-                  cleared. This is safe and won&apos;t affect model
-                  functionality.
-                </p>
-              </div>
-            </div>
-          </div>
-
-          <form action={handleDelete} className="space-y-4">
-            <input type="hidden" name="creator_id" value={creator.id} />
-
-            {error && (
-              <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-                {error}
-              </div>
-            )}
-
-            <Dialog.Footer>
-              <Button
-                variant="ghost"
-                size="small"
-                onClick={() => {
-                  setOpen(false);
-                  setError(null);
-                }}
-                disabled={isDeleting}
-                type="button"
-              >
-                Cancel
-              </Button>
-              <Button
-                type="submit"
-                variant="primary"
-                size="small"
-                disabled={isDeleting}
-                className="bg-destructive text-destructive-foreground hover:bg-destructive/90"
-              >
-                {isDeleting ? "Deleting..." : "Delete Creator"}
-              </Button>
-            </Dialog.Footer>
-          </form>
-        </div>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/DeleteModelModal.tsx

@@ -1,224 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { useRouter } from "next/navigation";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import { deleteLlmModelAction, fetchLlmModelUsage } from "../actions";
-
-export function DeleteModelModal({
-  model,
-  availableModels,
-}: {
-  model: LlmModel;
-  availableModels: LlmModel[];
-}) {
-  const router = useRouter();
-  const [open, setOpen] = useState(false);
-  const [selectedReplacement, setSelectedReplacement] = useState<string>("");
-  const [isDeleting, setIsDeleting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const [usageCount, setUsageCount] = useState<number | null>(null);
-  const [usageLoading, setUsageLoading] = useState(false);
-  const [usageError, setUsageError] = useState<string | null>(null);
-
-  // Filter out the current model and disabled models from replacement options
-  const replacementOptions = availableModels.filter(
-    (m) => m.id !== model.id && m.is_enabled,
-  );
-
-  // Check if migration is required (has blocks using this model)
-  const requiresMigration = usageCount !== null && usageCount > 0;
-
-  async function fetchUsage() {
-    setUsageLoading(true);
-    setUsageError(null);
-    try {
-      const usage = await fetchLlmModelUsage(model.id);
-      setUsageCount(usage.node_count);
-    } catch (err) {
-      console.error("Failed to fetch model usage:", err);
-      setUsageError("Failed to load usage count");
-      setUsageCount(null);
-    } finally {
-      setUsageLoading(false);
-    }
-  }
-
-  async function handleDelete(formData: FormData) {
-    setIsDeleting(true);
-    setError(null);
-    try {
-      await deleteLlmModelAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to delete model");
-    } finally {
-      setIsDeleting(false);
-    }
-  }
-
-  // Determine if delete button should be enabled
-  const canDelete =
-    !isDeleting &&
-    !usageLoading &&
-    usageCount !== null &&
-    (requiresMigration
-      ? selectedReplacement && replacementOptions.length > 0
-      : true);
-
-  return (
-    <Dialog
-      title="Delete Model"
-      controlled={{
-        isOpen: open,
-        set: async (isOpen) => {
-          setOpen(isOpen);
-          if (isOpen) {
-            setUsageCount(null);
-            setUsageError(null);
-            setError(null);
-            setSelectedReplacement("");
-            await fetchUsage();
-          }
-        },
-      }}
-      styling={{ maxWidth: "600px" }}
-    >
-      <Dialog.Trigger>
-        <Button
-          type="button"
-          variant="outline"
-          size="small"
-          className="min-w-0 text-destructive hover:bg-destructive/10"
-        >
-          Delete
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          {requiresMigration
-            ? "This action cannot be undone. All workflows using this model will be migrated to the replacement model you select."
-            : "This action cannot be undone."}
-        </div>
-
-        <div className="space-y-4">
-          <div className="rounded-lg border border-amber-500/30 bg-amber-500/10 p-4 dark:border-amber-400/30 dark:bg-amber-400/10">
-            <div className="flex items-start gap-3">
-              <div className="flex-shrink-0 text-amber-600 dark:text-amber-400">
-                ⚠️
-              </div>
-              <div className="text-sm text-foreground">
-                <p className="font-semibold">You are about to delete:</p>
-                <p className="mt-1">
-                  <span className="font-medium">{model.display_name}</span>{" "}
-                  <span className="text-muted-foreground">({model.slug})</span>
-                </p>
-                {usageLoading && (
-                  <p className="mt-2 text-muted-foreground">
-                    Loading usage count...
-                  </p>
-                )}
-                {usageError && (
-                  <p className="mt-2 text-destructive">{usageError}</p>
-                )}
-                {!usageLoading && !usageError && usageCount !== null && (
-                  <p className="mt-2 font-semibold">
-                    Impact: {usageCount} block{usageCount !== 1 ? "s" : ""}{" "}
-                    currently use this model
-                  </p>
-                )}
-                {requiresMigration && (
-                  <p className="mt-2 text-muted-foreground">
-                    All workflows currently using this model will be
-                    automatically updated to use the replacement model you
-                    choose below.
-                  </p>
-                )}
-                {!usageLoading && usageCount === 0 && (
-                  <p className="mt-2 text-muted-foreground">
-                    No workflows are using this model. It can be safely deleted.
-                  </p>
-                )}
-              </div>
-            </div>
-          </div>
-
-          <form action={handleDelete} className="space-y-4">
-            <input type="hidden" name="model_id" value={model.id} />
-            <input
-              type="hidden"
-              name="replacement_model_slug"
-              value={selectedReplacement}
-            />
-
-            {requiresMigration && (
-              <label className="text-sm font-medium">
-                <span className="mb-2 block">
-                  Select Replacement Model{" "}
-                  <span className="text-destructive">*</span>
-                </span>
-                <select
-                  required
-                  value={selectedReplacement}
-                  onChange={(e) => setSelectedReplacement(e.target.value)}
-                  className="w-full rounded border border-input bg-background p-2 text-sm"
-                >
-                  <option value="">-- Choose a replacement model --</option>
-                  {replacementOptions.map((m) => (
-                    <option key={m.id} value={m.slug}>
-                      {m.display_name} ({m.slug})
-                    </option>
-                  ))}
-                </select>
-                {replacementOptions.length === 0 && (
-                  <p className="mt-2 text-xs text-destructive">
-                    No replacement models available. You must have at least one
-                    other enabled model before deleting this one.
-                  </p>
-                )}
-              </label>
-            )}
-
-            {error && (
-              <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-                {error}
-              </div>
-            )}
-
-            <Dialog.Footer>
-              <Button
-                variant="ghost"
-                size="small"
-                type="button"
-                onClick={() => {
-                  setOpen(false);
-                  setSelectedReplacement("");
-                  setError(null);
-                }}
-                disabled={isDeleting}
-              >
-                Cancel
-              </Button>
-              <Button
-                type="submit"
-                variant="primary"
-                size="small"
-                disabled={!canDelete}
-                className="bg-destructive text-destructive-foreground hover:bg-destructive/90"
-              >
-                {isDeleting
-                  ? "Deleting..."
-                  : requiresMigration
-                    ? "Delete and Migrate"
-                    : "Delete"}
-              </Button>
-            </Dialog.Footer>
-          </form>
-        </div>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/DeleteProviderModal.tsx

@@ -1,129 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { useRouter } from "next/navigation";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import { deleteLlmProviderAction } from "../actions";
-
-export function DeleteProviderModal({ provider }: { provider: LlmProvider }) {
-  const [open, setOpen] = useState(false);
-  const [isDeleting, setIsDeleting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  const modelCount = provider.models?.length ?? 0;
-  const hasModels = modelCount > 0;
-
-  async function handleDelete(formData: FormData) {
-    setIsDeleting(true);
-    setError(null);
-    try {
-      await deleteLlmProviderAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(
-        err instanceof Error ? err.message : "Failed to delete provider",
-      );
-    } finally {
-      setIsDeleting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Delete Provider"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "480px" }}
-    >
-      <Dialog.Trigger>
-        <Button
-          type="button"
-          variant="outline"
-          size="small"
-          className="min-w-0 text-destructive hover:bg-destructive/10"
-        >
-          Delete
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="space-y-4">
-          <div
-            className={`rounded-lg border p-4 ${
-              hasModels
-                ? "border-destructive/30 bg-destructive/10"
-                : "border-amber-500/30 bg-amber-500/10 dark:border-amber-400/30 dark:bg-amber-400/10"
-            }`}
-          >
-            <div className="flex items-start gap-3">
-              <div
-                className={`flex-shrink-0 ${
-                  hasModels
-                    ? "text-destructive"
-                    : "text-amber-600 dark:text-amber-400"
-                }`}
-              >
-                {hasModels ? "🚫" : "⚠️"}
-              </div>
-              <div className="text-sm text-foreground">
-                <p className="font-semibold">You are about to delete:</p>
-                <p className="mt-1">
-                  <span className="font-medium">{provider.display_name}</span>{" "}
-                  <span className="text-muted-foreground">
-                    ({provider.name})
-                  </span>
-                </p>
-                {hasModels ? (
-                  <p className="mt-2 text-destructive">
-                    This provider has {modelCount} model(s). You must delete all
-                    models before you can delete this provider.
-                  </p>
-                ) : (
-                  <p className="mt-2 text-muted-foreground">
-                    This provider has no models and can be safely deleted.
-                  </p>
-                )}
-              </div>
-            </div>
-          </div>
-
-          <form action={handleDelete} className="space-y-4">
-            <input type="hidden" name="provider_id" value={provider.id} />
-
-            {error && (
-              <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-                {error}
-              </div>
-            )}
-
-            <Dialog.Footer>
-              <Button
-                variant="ghost"
-                size="small"
-                onClick={() => {
-                  setOpen(false);
-                  setError(null);
-                }}
-                disabled={isDeleting}
-                type="button"
-              >
-                Cancel
-              </Button>
-              <Button
-                type="submit"
-                variant="primary"
-                size="small"
-                disabled={isDeleting || hasModels}
-                className="bg-destructive text-destructive-foreground hover:bg-destructive/90 disabled:opacity-50"
-              >
-                {isDeleting ? "Deleting..." : "Delete Provider"}
-              </Button>
-            </Dialog.Footer>
-          </form>
-        </div>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/DisableModelModal.tsx

@@ -1,288 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import { toggleLlmModelAction, fetchLlmModelUsage } from "../actions";
-
-export function DisableModelModal({
-  model,
-  availableModels,
-}: {
-  model: LlmModel;
-  availableModels: LlmModel[];
-}) {
-  const [open, setOpen] = useState(false);
-  const [isDisabling, setIsDisabling] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const [usageCount, setUsageCount] = useState<number | null>(null);
-  const [selectedMigration, setSelectedMigration] = useState<string>("");
-  const [wantsMigration, setWantsMigration] = useState(false);
-  const [migrationReason, setMigrationReason] = useState("");
-  const [customCreditCost, setCustomCreditCost] = useState<string>("");
-
-  // Filter out the current model and disabled models from replacement options
-  const migrationOptions = availableModels.filter(
-    (m) => m.id !== model.id && m.is_enabled,
-  );
-
-  async function fetchUsage() {
-    try {
-      const usage = await fetchLlmModelUsage(model.id);
-      setUsageCount(usage.node_count);
-    } catch {
-      setUsageCount(null);
-    }
-  }
-
-  async function handleDisable(formData: FormData) {
-    setIsDisabling(true);
-    setError(null);
-    try {
-      await toggleLlmModelAction(formData);
-      setOpen(false);
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to disable model");
-    } finally {
-      setIsDisabling(false);
-    }
-  }
-
-  function resetState() {
-    setError(null);
-    setSelectedMigration("");
-    setWantsMigration(false);
-    setMigrationReason("");
-    setCustomCreditCost("");
-  }
-
-  const hasUsage = usageCount !== null && usageCount > 0;
-
-  return (
-    <Dialog
-      title="Disable Model"
-      controlled={{
-        isOpen: open,
-        set: async (isOpen) => {
-          setOpen(isOpen);
-          if (isOpen) {
-            setUsageCount(null);
-            resetState();
-            await fetchUsage();
-          }
-        },
-      }}
-      styling={{ maxWidth: "600px" }}
-    >
-      <Dialog.Trigger>
-        <Button
-          type="button"
-          variant="outline"
-          size="small"
-          className="min-w-0"
-        >
-          Disable
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Disabling a model will hide it from users when creating new workflows.
-        </div>
-
-        <div className="space-y-4">
-          <div className="rounded-lg border border-amber-500/30 bg-amber-500/10 p-4 dark:border-amber-400/30 dark:bg-amber-400/10">
-            <div className="flex items-start gap-3">
-              <div className="flex-shrink-0 text-amber-600 dark:text-amber-400">
-                ⚠️
-              </div>
-              <div className="text-sm text-foreground">
-                <p className="font-semibold">You are about to disable:</p>
-                <p className="mt-1">
-                  <span className="font-medium">{model.display_name}</span>{" "}
-                  <span className="text-muted-foreground">({model.slug})</span>
-                </p>
-                {usageCount === null ? (
-                  <p className="mt-2 text-muted-foreground">
-                    Loading usage data...
-                  </p>
-                ) : usageCount > 0 ? (
-                  <p className="mt-2 font-semibold">
-                    Impact: {usageCount} block{usageCount !== 1 ? "s" : ""}{" "}
-                    currently use this model
-                  </p>
-                ) : (
-                  <p className="mt-2 text-muted-foreground">
-                    No workflows are currently using this model.
-                  </p>
-                )}
-              </div>
-            </div>
-          </div>
-
-          {hasUsage && (
-            <div className="space-y-4 rounded-lg border border-border bg-muted/50 p-4">
-              <label className="flex items-start gap-3">
-                <input
-                  type="checkbox"
-                  checked={wantsMigration}
-                  onChange={(e) => {
-                    setWantsMigration(e.target.checked);
-                    if (!e.target.checked) {
-                      setSelectedMigration("");
-                    }
-                  }}
-                  className="mt-1"
-                />
-                <div className="text-sm">
-                  <span className="font-medium">
-                    Migrate existing workflows to another model
-                  </span>
-                  <p className="mt-1 text-muted-foreground">
-                    Creates a revertible migration record. If unchecked,
-                    existing workflows will use automatic fallback to an enabled
-                    model from the same provider.
-                  </p>
-                </div>
-              </label>
-
-              {wantsMigration && (
-                <div className="space-y-4 border-t border-border pt-4">
-                  <label className="block text-sm font-medium">
-                    <span className="mb-2 block">
-                      Replacement Model{" "}
-                      <span className="text-destructive">*</span>
-                    </span>
-                    <select
-                      required
-                      value={selectedMigration}
-                      onChange={(e) => setSelectedMigration(e.target.value)}
-                      className="w-full rounded border border-input bg-background p-2 text-sm"
-                    >
-                      <option value="">-- Choose a replacement model --</option>
-                      {migrationOptions.map((m) => (
-                        <option key={m.id} value={m.slug}>
-                          {m.display_name} ({m.slug})
-                        </option>
-                      ))}
-                    </select>
-                    {migrationOptions.length === 0 && (
-                      <p className="mt-2 text-xs text-destructive">
-                        No other enabled models available for migration.
-                      </p>
-                    )}
-                  </label>
-
-                  <label className="block text-sm font-medium">
-                    <span className="mb-2 block">
-                      Migration Reason{" "}
-                      <span className="font-normal text-muted-foreground">
-                        (optional)
-                      </span>
-                    </span>
-                    <input
-                      type="text"
-                      value={migrationReason}
-                      onChange={(e) => setMigrationReason(e.target.value)}
-                      placeholder="e.g., Provider outage, Cost reduction"
-                      className="w-full rounded border border-input bg-background p-2 text-sm"
-                    />
-                    <p className="mt-1 text-xs text-muted-foreground">
-                      Helps track why the migration was made
-                    </p>
-                  </label>
-
-                  <label className="block text-sm font-medium">
-                    <span className="mb-2 block">
-                      Custom Credit Cost{" "}
-                      <span className="font-normal text-muted-foreground">
-                        (optional)
-                      </span>
-                    </span>
-                    <input
-                      type="number"
-                      min="0"
-                      value={customCreditCost}
-                      onChange={(e) => setCustomCreditCost(e.target.value)}
-                      placeholder="Leave blank to use target model's cost"
-                      className="w-full rounded border border-input bg-background p-2 text-sm"
-                    />
-                    <p className="mt-1 text-xs text-muted-foreground">
-                      Override pricing for migrated workflows. When set, billing
-                      will use this cost instead of the target model&apos;s
-                      cost.
-                    </p>
-                  </label>
-                </div>
-              )}
-            </div>
-          )}
-
-          <form action={handleDisable} className="space-y-4">
-            <input type="hidden" name="model_id" value={model.id} />
-            <input type="hidden" name="is_enabled" value="false" />
-            {wantsMigration && selectedMigration && (
-              <>
-                <input
-                  type="hidden"
-                  name="migrate_to_slug"
-                  value={selectedMigration}
-                />
-                {migrationReason && (
-                  <input
-                    type="hidden"
-                    name="migration_reason"
-                    value={migrationReason}
-                  />
-                )}
-                {customCreditCost && (
-                  <input
-                    type="hidden"
-                    name="custom_credit_cost"
-                    value={customCreditCost}
-                  />
-                )}
-              </>
-            )}
-
-            {error && (
-              <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-                {error}
-              </div>
-            )}
-
-            <Dialog.Footer>
-              <Button
-                variant="ghost"
-                size="small"
-                onClick={() => {
-                  setOpen(false);
-                  resetState();
-                }}
-                disabled={isDisabling}
-              >
-                Cancel
-              </Button>
-              <Button
-                type="submit"
-                variant="primary"
-                size="small"
-                disabled={
-                  isDisabling ||
-                  (wantsMigration && !selectedMigration) ||
-                  usageCount === null
-                }
-              >
-                {isDisabling
-                  ? "Disabling..."
-                  : wantsMigration && selectedMigration
-                    ? "Disable & Migrate"
-                    : "Disable Model"}
-              </Button>
-            </Dialog.Footer>
-          </form>
-        </div>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/EditModelModal.tsx

@@ -1,223 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { useRouter } from "next/navigation";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import { updateLlmModelAction } from "../actions";
-
-export function EditModelModal({
-  model,
-  providers,
-  creators,
-}: {
-  model: LlmModel;
-  providers: LlmProvider[];
-  creators: LlmModelCreator[];
-}) {
-  const router = useRouter();
-  const [open, setOpen] = useState(false);
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const cost = model.costs?.[0];
-  const provider = providers.find((p) => p.id === model.provider_id);
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await updateLlmModelAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to update model");
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Edit Model"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "768px", maxHeight: "90vh", overflowY: "auto" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="outline" size="small" className="min-w-0">
-          Edit
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Update model metadata and pricing information.
-        </div>
-        {error && (
-          <div className="mb-4 rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-            {error}
-          </div>
-        )}
-        <form action={handleSubmit} className="space-y-4">
-          <input type="hidden" name="model_id" value={model.id} />
-
-          <div className="grid gap-4 md:grid-cols-2">
-            <label className="text-sm font-medium">
-              Display Name
-              <input
-                required
-                name="display_name"
-                defaultValue={model.display_name}
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-              />
-            </label>
-            <label className="text-sm font-medium">
-              Provider
-              <select
-                required
-                name="provider_id"
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-                defaultValue={model.provider_id}
-              >
-                {providers.map((p) => (
-                  <option key={p.id} value={p.id}>
-                    {p.display_name} ({p.name})
-                  </option>
-                ))}
-              </select>
-              <span className="text-xs text-muted-foreground">
-                Who hosts/serves the model
-              </span>
-            </label>
-          </div>
-
-          <div className="grid gap-4 md:grid-cols-2">
-            <label className="text-sm font-medium">
-              Creator
-              <select
-                name="creator_id"
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-                defaultValue={model.creator_id ?? ""}
-              >
-                <option value="">No creator selected</option>
-                {creators.map((c) => (
-                  <option key={c.id} value={c.id}>
-                    {c.display_name} ({c.name})
-                  </option>
-                ))}
-              </select>
-              <span className="text-xs text-muted-foreground">
-                Who made/trained the model (e.g., OpenAI, Meta)
-              </span>
-            </label>
-          </div>
-
-          <label className="text-sm font-medium">
-            Description
-            <textarea
-              name="description"
-              rows={2}
-              defaultValue={model.description ?? ""}
-              className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-              placeholder="Optional description..."
-            />
-          </label>
-
-          <div className="grid gap-4 md:grid-cols-2">
-            <label className="text-sm font-medium">
-              Context Window
-              <input
-                required
-                type="number"
-                name="context_window"
-                defaultValue={model.context_window}
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-                min={1}
-              />
-            </label>
-            <label className="text-sm font-medium">
-              Max Output Tokens
-              <input
-                type="number"
-                name="max_output_tokens"
-                defaultValue={model.max_output_tokens ?? undefined}
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-                min={1}
-              />
-            </label>
-          </div>
-
-          <div className="grid gap-4 md:grid-cols-2">
-            <label className="text-sm font-medium">
-              Credit Cost
-              <input
-                required
-                type="number"
-                name="credit_cost"
-                defaultValue={cost?.credit_cost ?? 0}
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-                min={0}
-              />
-              <span className="text-xs text-muted-foreground">
-                Credits charged per run
-              </span>
-            </label>
-            <label className="text-sm font-medium">
-              Credential Provider
-              <select
-                required
-                name="credential_provider"
-                defaultValue={cost?.credential_provider ?? provider?.name ?? ""}
-                className="mt-1 w-full rounded border border-input bg-background p-2 text-sm"
-              >
-                <option value="" disabled>
-                  Select provider
-                </option>
-                {providers.map((p) => (
-                  <option key={p.id} value={p.name}>
-                    {p.display_name} ({p.name})
-                  </option>
-                ))}
-              </select>
-              <span className="text-xs text-muted-foreground">
-                Must match a key in PROVIDER_CREDENTIALS
-              </span>
-            </label>
-          </div>
-          {/* Hidden defaults for credential_type and unit */}
-          <input
-            type="hidden"
-            name="credential_type"
-            value={
-              cost?.credential_type ??
-              provider?.default_credential_type ??
-              "api_key"
-            }
-          />
-          <input type="hidden" name="unit" value={cost?.unit ?? "RUN"} />
-
-          <Dialog.Footer>
-            <Button
-              type="button"
-              variant="ghost"
-              size="small"
-              onClick={() => setOpen(false)}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Updating..." : "Update Model"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/EditProviderModal.tsx

@@ -1,263 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Button } from "@/components/atoms/Button/Button";
-import { updateLlmProviderAction } from "../actions";
-import { useRouter } from "next/navigation";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-
-export function EditProviderModal({ provider }: { provider: LlmProvider }) {
-  const [open, setOpen] = useState(false);
-  const [isSubmitting, setIsSubmitting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-  const router = useRouter();
-
-  async function handleSubmit(formData: FormData) {
-    setIsSubmitting(true);
-    setError(null);
-    try {
-      await updateLlmProviderAction(formData);
-      setOpen(false);
-      router.refresh();
-    } catch (err) {
-      setError(
-        err instanceof Error ? err.message : "Failed to update provider",
-      );
-    } finally {
-      setIsSubmitting(false);
-    }
-  }
-
-  return (
-    <Dialog
-      title="Edit Provider"
-      controlled={{ isOpen: open, set: setOpen }}
-      styling={{ maxWidth: "768px", maxHeight: "90vh", overflowY: "auto" }}
-    >
-      <Dialog.Trigger>
-        <Button variant="outline" size="small">
-          Edit
-        </Button>
-      </Dialog.Trigger>
-      <Dialog.Content>
-        <div className="mb-4 text-sm text-muted-foreground">
-          Update provider configuration and capabilities.
-        </div>
-
-        <form action={handleSubmit} className="space-y-6">
-          <input type="hidden" name="provider_id" value={provider.id} />
-
-          {/* Basic Information */}
-          <div className="space-y-4">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Basic Information
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Core provider details
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="name"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Provider Slug <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="name"
-                  required
-                  name="name"
-                  defaultValue={provider.name}
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="e.g. openai"
-                />
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="display_name"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Display Name <span className="text-destructive">*</span>
-                </label>
-                <input
-                  id="display_name"
-                  required
-                  name="display_name"
-                  defaultValue={provider.display_name}
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="OpenAI"
-                />
-              </div>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="description"
-                className="text-sm font-medium text-foreground"
-              >
-                Description
-              </label>
-              <textarea
-                id="description"
-                name="description"
-                rows={3}
-                defaultValue={provider.description ?? ""}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="Optional description..."
-              />
-            </div>
-          </div>
-
-          {/* Default Credentials */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Default Credentials
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Credential provider name that matches the key in{" "}
-                <code className="rounded bg-muted px-1 py-0.5 font-mono text-xs">
-                  PROVIDER_CREDENTIALS
-                </code>
-              </p>
-            </div>
-            <div className="grid gap-4 sm:grid-cols-2">
-              <div className="space-y-2">
-                <label
-                  htmlFor="default_credential_provider"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Credential Provider
-                </label>
-                <input
-                  id="default_credential_provider"
-                  name="default_credential_provider"
-                  defaultValue={provider.default_credential_provider ?? ""}
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="openai"
-                />
-              </div>
-              <div className="space-y-2">
-                <label
-                  htmlFor="default_credential_id"
-                  className="text-sm font-medium text-foreground"
-                >
-                  Credential ID
-                </label>
-                <input
-                  id="default_credential_id"
-                  name="default_credential_id"
-                  defaultValue={provider.default_credential_id ?? ""}
-                  className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                  placeholder="Optional credential ID"
-                />
-              </div>
-            </div>
-            <div className="space-y-2">
-              <label
-                htmlFor="default_credential_type"
-                className="text-sm font-medium text-foreground"
-              >
-                Credential Type
-              </label>
-              <input
-                id="default_credential_type"
-                name="default_credential_type"
-                defaultValue={provider.default_credential_type ?? "api_key"}
-                className="w-full rounded-md border border-input bg-background px-3 py-2 text-sm transition-colors placeholder:text-muted-foreground focus:border-primary focus:outline-none focus:ring-2 focus:ring-primary/20"
-                placeholder="api_key"
-              />
-            </div>
-          </div>
-
-          {/* Capabilities */}
-          <div className="space-y-4 border-t border-border pt-6">
-            <div className="space-y-1">
-              <h3 className="text-sm font-semibold text-foreground">
-                Capabilities
-              </h3>
-              <p className="text-xs text-muted-foreground">
-                Provider feature flags
-              </p>
-            </div>
-            <div className="grid gap-3 sm:grid-cols-2">
-              {[
-                {
-                  name: "supports_tools",
-                  label: "Supports tools",
-                  checked: provider.supports_tools,
-                },
-                {
-                  name: "supports_json_output",
-                  label: "Supports JSON output",
-                  checked: provider.supports_json_output,
-                },
-                {
-                  name: "supports_reasoning",
-                  label: "Supports reasoning",
-                  checked: provider.supports_reasoning,
-                },
-                {
-                  name: "supports_parallel_tool",
-                  label: "Supports parallel tool calls",
-                  checked: provider.supports_parallel_tool,
-                },
-              ].map(({ name, label, checked }) => (
-                <div
-                  key={name}
-                  className="flex items-center gap-3 rounded-md border border-border bg-muted/30 px-4 py-3 transition-colors hover:bg-muted/50"
-                >
-                  <input type="hidden" name={name} value="off" />
-                  <input
-                    id={name}
-                    type="checkbox"
-                    name={name}
-                    defaultChecked={checked}
-                    className="h-4 w-4 rounded border-input"
-                  />
-                  <label
-                    htmlFor={name}
-                    className="text-sm font-medium text-foreground"
-                  >
-                    {label}
-                  </label>
-                </div>
-              ))}
-            </div>
-          </div>
-
-          {error && (
-            <div className="rounded-lg border border-destructive/30 bg-destructive/10 p-3 text-sm text-destructive">
-              {error}
-            </div>
-          )}
-
-          <Dialog.Footer>
-            <Button
-              variant="ghost"
-              size="small"
-              type="button"
-              onClick={() => {
-                setOpen(false);
-                setError(null);
-              }}
-              disabled={isSubmitting}
-            >
-              Cancel
-            </Button>
-            <Button
-              variant="primary"
-              size="small"
-              type="submit"
-              disabled={isSubmitting}
-            >
-              {isSubmitting ? "Saving..." : "Save Changes"}
-            </Button>
-          </Dialog.Footer>
-        </form>
-      </Dialog.Content>
-    </Dialog>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/LlmRegistryDashboard.tsx

@@ -1,131 +0,0 @@
-"use client";
-
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import type { LlmModelMigration } from "@/app/api/__generated__/models/llmModelMigration";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import { ErrorBoundary } from "@/components/molecules/ErrorBoundary/ErrorBoundary";
-import { ErrorCard } from "@/components/molecules/ErrorCard/ErrorCard";
-import { AddProviderModal } from "./AddProviderModal";
-import { AddModelModal } from "./AddModelModal";
-import { AddCreatorModal } from "./AddCreatorModal";
-import { ProviderList } from "./ProviderList";
-import { ModelsTable } from "./ModelsTable";
-import { MigrationsTable } from "./MigrationsTable";
-import { CreatorsTable } from "./CreatorsTable";
-import { RecommendedModelSelector } from "./RecommendedModelSelector";
-
-interface Props {
-  providers: LlmProvider[];
-  models: LlmModel[];
-  migrations: LlmModelMigration[];
-  creators: LlmModelCreator[];
-}
-
-function AdminErrorFallback() {
-  return (
-    <div className="mx-auto max-w-xl p-6">
-      <ErrorCard
-        responseError={{
-          message:
-            "An error occurred while loading the LLM Registry. Please refresh the page.",
-        }}
-        context="llm-registry"
-        onRetry={() => window.location.reload()}
-      />
-    </div>
-  );
-}
-
-export function LlmRegistryDashboard({
-  providers,
-  models,
-  migrations,
-  creators,
-}: Props) {
-  return (
-    <ErrorBoundary fallback={<AdminErrorFallback />} context="llm-registry">
-      <div className="mx-auto p-6">
-        <div className="flex flex-col gap-6">
-          {/* Header */}
-          <div>
-            <h1 className="text-3xl font-bold">LLM Registry</h1>
-            <p className="text-muted-foreground">
-              Manage providers, creators, models, and credit pricing
-            </p>
-          </div>
-
-          {/* Active Migrations Section - Only show if there are migrations */}
-          {migrations.length > 0 && (
-            <div className="rounded-lg border border-primary/30 bg-primary/5 p-6 shadow-sm">
-              <div className="mb-4">
-                <h2 className="text-xl font-semibold">Active Migrations</h2>
-                <p className="mt-1 text-sm text-muted-foreground">
-                  These migrations can be reverted to restore workflows to their
-                  original model
-                </p>
-              </div>
-              <MigrationsTable migrations={migrations} />
-            </div>
-          )}
-
-          {/* Providers & Creators Section - Side by Side */}
-          <div className="grid gap-6 lg:grid-cols-2">
-            {/* Providers */}
-            <div className="rounded-lg border bg-card p-6 shadow-sm">
-              <div className="mb-4 flex items-center justify-between">
-                <div>
-                  <h2 className="text-xl font-semibold">Providers</h2>
-                  <p className="mt-1 text-sm text-muted-foreground">
-                    Who hosts/serves the models
-                  </p>
-                </div>
-                <AddProviderModal />
-              </div>
-              <ProviderList providers={providers} />
-            </div>
-
-            {/* Creators */}
-            <div className="rounded-lg border bg-card p-6 shadow-sm">
-              <div className="mb-4 flex items-center justify-between">
-                <div>
-                  <h2 className="text-xl font-semibold">Creators</h2>
-                  <p className="mt-1 text-sm text-muted-foreground">
-                    Who made/trained the models
-                  </p>
-                </div>
-                <AddCreatorModal />
-              </div>
-              <CreatorsTable creators={creators} />
-            </div>
-          </div>
-
-          {/* Models Section */}
-          <div className="rounded-lg border bg-card p-6 shadow-sm">
-            <div className="mb-4 flex items-center justify-between">
-              <div>
-                <h2 className="text-xl font-semibold">Models</h2>
-                <p className="mt-1 text-sm text-muted-foreground">
-                  Toggle availability, adjust context windows, and update credit
-                  pricing
-                </p>
-              </div>
-              <AddModelModal providers={providers} creators={creators} />
-            </div>
-
-            {/* Recommended Model Selector */}
-            <div className="mb-6">
-              <RecommendedModelSelector models={models} />
-            </div>
-
-            <ModelsTable
-              models={models}
-              providers={providers}
-              creators={creators}
-            />
-          </div>
-        </div>
-      </div>
-    </ErrorBoundary>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/MigrationsTable.tsx

@@ -1,133 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import type { LlmModelMigration } from "@/app/api/__generated__/models/llmModelMigration";
-import { Button } from "@/components/atoms/Button/Button";
-import {
-  Table,
-  TableBody,
-  TableCell,
-  TableHead,
-  TableHeader,
-  TableRow,
-} from "@/components/atoms/Table/Table";
-import { revertLlmMigrationAction } from "../actions";
-
-export function MigrationsTable({
-  migrations,
-}: {
-  migrations: LlmModelMigration[];
-}) {
-  if (!migrations.length) {
-    return (
-      <div className="rounded-lg border border-dashed border-border p-6 text-center text-sm text-muted-foreground">
-        No active migrations. Migrations are created when you disable a model
-        with the &quot;Migrate existing workflows&quot; option.
-      </div>
-    );
-  }
-
-  return (
-    <div className="rounded-lg border">
-      <Table>
-        <TableHeader>
-          <TableRow>
-            <TableHead>Migration</TableHead>
-            <TableHead>Reason</TableHead>
-            <TableHead>Nodes Affected</TableHead>
-            <TableHead>Custom Cost</TableHead>
-            <TableHead>Created</TableHead>
-            <TableHead className="text-right">Actions</TableHead>
-          </TableRow>
-        </TableHeader>
-        <TableBody>
-          {migrations.map((migration) => (
-            <MigrationRow key={migration.id} migration={migration} />
-          ))}
-        </TableBody>
-      </Table>
-    </div>
-  );
-}
-
-function MigrationRow({ migration }: { migration: LlmModelMigration }) {
-  const [isReverting, setIsReverting] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-
-  async function handleRevert(formData: FormData) {
-    setIsReverting(true);
-    setError(null);
-    try {
-      await revertLlmMigrationAction(formData);
-    } catch (err) {
-      setError(
-        err instanceof Error ? err.message : "Failed to revert migration",
-      );
-    } finally {
-      setIsReverting(false);
-    }
-  }
-
-  const createdDate = new Date(migration.created_at);
-
-  return (
-    <>
-      <TableRow>
-        <TableCell>
-          <div className="text-sm">
-            <span className="font-medium">{migration.source_model_slug}</span>
-            <span className="mx-2 text-muted-foreground">→</span>
-            <span className="font-medium">{migration.target_model_slug}</span>
-          </div>
-        </TableCell>
-        <TableCell>
-          <div className="text-sm text-muted-foreground">
-            {migration.reason || "—"}
-          </div>
-        </TableCell>
-        <TableCell>
-          <div className="text-sm">{migration.node_count}</div>
-        </TableCell>
-        <TableCell>
-          <div className="text-sm">
-            {migration.custom_credit_cost !== null &&
-            migration.custom_credit_cost !== undefined
-              ? `${migration.custom_credit_cost} credits`
-              : "—"}
-          </div>
-        </TableCell>
-        <TableCell>
-          <div className="text-sm text-muted-foreground">
-            {createdDate.toLocaleDateString()}{" "}
-            {createdDate.toLocaleTimeString([], {
-              hour: "2-digit",
-              minute: "2-digit",
-            })}
-          </div>
-        </TableCell>
-        <TableCell className="text-right">
-          <form action={handleRevert} className="inline">
-            <input type="hidden" name="migration_id" value={migration.id} />
-            <Button
-              type="submit"
-              variant="outline"
-              size="small"
-              disabled={isReverting}
-            >
-              {isReverting ? "Reverting..." : "Revert"}
-            </Button>
-          </form>
-        </TableCell>
-      </TableRow>
-      {error && (
-        <TableRow>
-          <TableCell colSpan={6}>
-            <div className="rounded border border-destructive/30 bg-destructive/10 p-2 text-sm text-destructive">
-              {error}
-            </div>
-          </TableCell>
-        </TableRow>
-      )}
-    </>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/ModelsTable.tsx

@@ -1,265 +0,0 @@
-"use client";
-
-import { useState, useEffect, useRef } from "react";
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import type { LlmModelCreator } from "@/app/api/__generated__/models/llmModelCreator";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import {
-  Table,
-  TableBody,
-  TableCell,
-  TableHead,
-  TableHeader,
-  TableRow,
-} from "@/components/atoms/Table/Table";
-import { Button } from "@/components/atoms/Button/Button";
-import { toggleLlmModelAction } from "../actions";
-import { DeleteModelModal } from "./DeleteModelModal";
-import { DisableModelModal } from "./DisableModelModal";
-import { EditModelModal } from "./EditModelModal";
-import { Star, Spinner } from "@phosphor-icons/react";
-import { getV2ListLlmModels } from "@/app/api/__generated__/endpoints/admin/admin";
-
-const PAGE_SIZE = 50;
-
-export function ModelsTable({
-  models: initialModels,
-  providers,
-  creators,
-}: {
-  models: LlmModel[];
-  providers: LlmProvider[];
-  creators: LlmModelCreator[];
-}) {
-  const [models, setModels] = useState<LlmModel[]>(initialModels);
-  const [currentPage, setCurrentPage] = useState(1);
-  const [hasMore, setHasMore] = useState(initialModels.length === PAGE_SIZE);
-  const [isLoading, setIsLoading] = useState(false);
-  const loadedPagesRef = useRef(1);
-
-  // Sync with parent when initialModels changes (e.g., after enable/disable)
-  // Re-fetch all loaded pages to preserve expanded state
-  useEffect(() => {
-    async function refetchAllPages() {
-      const pagesToLoad = loadedPagesRef.current;
-
-      if (pagesToLoad === 1) {
-        // Only first page loaded, just use initialModels
-        setModels(initialModels);
-        setHasMore(initialModels.length === PAGE_SIZE);
-        return;
-      }
-
-      // Re-fetch all pages we had loaded
-      const allModels: LlmModel[] = [...initialModels];
-      let lastPageHadFullResults = initialModels.length === PAGE_SIZE;
-
-      for (let page = 2; page <= pagesToLoad; page++) {
-        try {
-          const response = await getV2ListLlmModels({
-            page,
-            page_size: PAGE_SIZE,
-          });
-          if (response.status === 200) {
-            allModels.push(...response.data.models);
-            lastPageHadFullResults = response.data.models.length === PAGE_SIZE;
-          }
-        } catch (err) {
-          console.error(`Error refetching page ${page}:`, err);
-          break;
-        }
-      }
-
-      setModels(allModels);
-      setHasMore(lastPageHadFullResults);
-    }
-
-    refetchAllPages();
-  }, [initialModels]);
-
-  async function loadMore() {
-    if (isLoading) return;
-    setIsLoading(true);
-
-    try {
-      const nextPage = currentPage + 1;
-      const response = await getV2ListLlmModels({
-        page: nextPage,
-        page_size: PAGE_SIZE,
-      });
-
-      if (response.status === 200) {
-        setModels((prev) => [...prev, ...response.data.models]);
-        setCurrentPage(nextPage);
-        loadedPagesRef.current = nextPage;
-        setHasMore(response.data.models.length === PAGE_SIZE);
-      }
-    } catch (err) {
-      console.error("Error loading more models:", err);
-    } finally {
-      setIsLoading(false);
-    }
-  }
-  if (!models.length) {
-    return (
-      <div className="rounded-lg border border-dashed border-border p-6 text-center text-sm text-muted-foreground">
-        No models registered yet.
-      </div>
-    );
-  }
-
-  const providerLookup = new Map(
-    providers.map((provider) => [provider.id, provider]),
-  );
-
-  return (
-    <div>
-      <div className="rounded-lg border">
-        <Table>
-          <TableHeader>
-            <TableRow>
-              <TableHead>Model</TableHead>
-              <TableHead>Provider</TableHead>
-              <TableHead>Creator</TableHead>
-              <TableHead>Context Window</TableHead>
-              <TableHead>Max Output</TableHead>
-              <TableHead>Cost</TableHead>
-              <TableHead>Status</TableHead>
-              <TableHead>Actions</TableHead>
-            </TableRow>
-          </TableHeader>
-          <TableBody>
-            {models.map((model) => {
-              const cost = model.costs?.[0];
-              const provider = providerLookup.get(model.provider_id);
-              return (
-                <TableRow
-                  key={model.id}
-                  className={model.is_enabled ? "" : "opacity-60"}
-                >
-                  <TableCell>
-                    <div className="font-medium">{model.display_name}</div>
-                    <div className="text-xs text-muted-foreground">
-                      {model.slug}
-                    </div>
-                  </TableCell>
-                  <TableCell>
-                    {provider ? (
-                      <>
-                        <div>{provider.display_name}</div>
-                        <div className="text-xs text-muted-foreground">
-                          {provider.name}
-                        </div>
-                      </>
-                    ) : (
-                      model.provider_id
-                    )}
-                  </TableCell>
-                  <TableCell>
-                    {model.creator ? (
-                      <>
-                        <div>{model.creator.display_name}</div>
-                        <div className="text-xs text-muted-foreground">
-                          {model.creator.name}
-                        </div>
-                      </>
-                    ) : (
-                      <span className="text-muted-foreground">—</span>
-                    )}
-                  </TableCell>
-                  <TableCell>{model.context_window.toLocaleString()}</TableCell>
-                  <TableCell>
-                    {model.max_output_tokens
-                      ? model.max_output_tokens.toLocaleString()
-                      : "—"}
-                  </TableCell>
-                  <TableCell>
-                    {cost ? (
-                      <>
-                        <div className="font-medium">
-                          {cost.credit_cost} credits
-                        </div>
-                        <div className="text-xs text-muted-foreground">
-                          {cost.credential_provider}
-                        </div>
-                      </>
-                    ) : (
-                      "—"
-                    )}
-                  </TableCell>
-                  <TableCell>
-                    <div className="flex flex-col gap-1">
-                      <span
-                        className={`inline-flex rounded-full px-2.5 py-1 text-xs font-semibold ${
-                          model.is_enabled
-                            ? "bg-primary/10 text-primary"
-                            : "bg-muted text-muted-foreground"
-                        }`}
-                      >
-                        {model.is_enabled ? "Enabled" : "Disabled"}
-                      </span>
-                      {model.is_recommended && (
-                        <span className="inline-flex items-center gap-1 rounded-full bg-amber-500/10 px-2.5 py-1 text-xs font-semibold text-amber-600 dark:text-amber-400">
-                          <Star size={12} weight="fill" />
-                          Recommended
-                        </span>
-                      )}
-                    </div>
-                  </TableCell>
-                  <TableCell>
-                    <div className="flex items-center justify-end gap-2">
-                      {model.is_enabled ? (
-                        <DisableModelModal
-                          model={model}
-                          availableModels={models}
-                        />
-                      ) : (
-                        <EnableModelButton modelId={model.id} />
-                      )}
-                      <EditModelModal
-                        model={model}
-                        providers={providers}
-                        creators={creators}
-                      />
-                      <DeleteModelModal
-                        model={model}
-                        availableModels={models}
-                      />
-                    </div>
-                  </TableCell>
-                </TableRow>
-              );
-            })}
-          </TableBody>
-        </Table>
-      </div>
-
-      {hasMore && (
-        <div className="mt-4 flex justify-center">
-          <Button onClick={loadMore} disabled={isLoading} variant="outline">
-            {isLoading ? (
-              <>
-                <Spinner className="mr-2 h-4 w-4 animate-spin" />
-                Loading...
-              </>
-            ) : (
-              "Load More"
-            )}
-          </Button>
-        </div>
-      )}
-    </div>
-  );
-}
-
-function EnableModelButton({ modelId }: { modelId: string }) {
-  return (
-    <form action={toggleLlmModelAction} className="inline">
-      <input type="hidden" name="model_id" value={modelId} />
-      <input type="hidden" name="is_enabled" value="true" />
-      <Button type="submit" variant="outline" size="small" className="min-w-0">
-        Enable
-      </Button>
-    </form>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/ProviderList.tsx

@@ -1,94 +0,0 @@
-"use client";
-
-import {
-  Table,
-  TableBody,
-  TableCell,
-  TableHead,
-  TableHeader,
-  TableRow,
-} from "@/components/atoms/Table/Table";
-import type { LlmProvider } from "@/app/api/__generated__/models/llmProvider";
-import { DeleteProviderModal } from "./DeleteProviderModal";
-import { EditProviderModal } from "./EditProviderModal";
-
-export function ProviderList({ providers }: { providers: LlmProvider[] }) {
-  if (!providers.length) {
-    return (
-      <div className="rounded-lg border border-dashed border-border p-6 text-center text-sm text-muted-foreground">
-        No providers configured yet.
-      </div>
-    );
-  }
-
-  return (
-    <div className="rounded-lg border">
-      <Table>
-        <TableHeader>
-          <TableRow>
-            <TableHead>Name</TableHead>
-            <TableHead>Display Name</TableHead>
-            <TableHead>Default Credential</TableHead>
-            <TableHead>Capabilities</TableHead>
-            <TableHead>Models</TableHead>
-            <TableHead className="w-[100px]">Actions</TableHead>
-          </TableRow>
-        </TableHeader>
-        <TableBody>
-          {providers.map((provider) => (
-            <TableRow key={provider.id}>
-              <TableCell className="font-medium">{provider.name}</TableCell>
-              <TableCell>{provider.display_name}</TableCell>
-              <TableCell>
-                {provider.default_credential_provider
-                  ? `${provider.default_credential_provider} (${provider.default_credential_id ?? "id?"})`
-                  : "—"}
-              </TableCell>
-              <TableCell className="text-sm text-muted-foreground">
-                <div className="flex flex-wrap gap-2">
-                  {provider.supports_tools && (
-                    <span className="rounded bg-muted px-2 py-0.5 text-xs">
-                      Tools
-                    </span>
-                  )}
-                  {provider.supports_json_output && (
-                    <span className="rounded bg-muted px-2 py-0.5 text-xs">
-                      JSON
-                    </span>
-                  )}
-                  {provider.supports_reasoning && (
-                    <span className="rounded bg-muted px-2 py-0.5 text-xs">
-                      Reasoning
-                    </span>
-                  )}
-                  {provider.supports_parallel_tool && (
-                    <span className="rounded bg-muted px-2 py-0.5 text-xs">
-                      Parallel Tools
-                    </span>
-                  )}
-                </div>
-              </TableCell>
-              <TableCell className="text-sm">
-                <span
-                  className={
-                    (provider.models?.length ?? 0) > 0
-                      ? "text-foreground"
-                      : "text-muted-foreground"
-                  }
-                >
-                  {provider.models?.length ?? 0}
-                </span>
-              </TableCell>
-              <TableCell>
-                <div className="flex gap-2">
-                  <EditProviderModal provider={provider} />
-                  <DeleteProviderModal provider={provider} />
-                </div>
-              </TableCell>
-            </TableRow>
-          ))}
-        </TableBody>
-      </Table>
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/components/RecommendedModelSelector.tsx

@@ -1,87 +0,0 @@
-"use client";
-
-import { useState } from "react";
-import { useRouter } from "next/navigation";
-import type { LlmModel } from "@/app/api/__generated__/models/llmModel";
-import { Button } from "@/components/atoms/Button/Button";
-import { setRecommendedModelAction } from "../actions";
-import { Star } from "@phosphor-icons/react";
-
-export function RecommendedModelSelector({ models }: { models: LlmModel[] }) {
-  const router = useRouter();
-  const enabledModels = models.filter((m) => m.is_enabled);
-  const currentRecommended = models.find((m) => m.is_recommended);
-
-  const [selectedModelId, setSelectedModelId] = useState<string>(
-    currentRecommended?.id || "",
-  );
-  const [isSaving, setIsSaving] = useState(false);
-  const [error, setError] = useState<string | null>(null);
-
-  const hasChanges = selectedModelId !== (currentRecommended?.id || "");
-
-  async function handleSave() {
-    if (!selectedModelId) return;
-
-    setIsSaving(true);
-    setError(null);
-    try {
-      const formData = new FormData();
-      formData.set("model_id", selectedModelId);
-      await setRecommendedModelAction(formData);
-      router.refresh();
-    } catch (err) {
-      setError(err instanceof Error ? err.message : "Failed to save");
-    } finally {
-      setIsSaving(false);
-    }
-  }
-
-  return (
-    <div className="rounded-lg border border-border bg-card p-4">
-      <div className="mb-3 flex items-center gap-2">
-        <Star size={20} weight="fill" className="text-amber-500" />
-        <h3 className="text-sm font-semibold">Recommended Model</h3>
-      </div>
-      <p className="mb-3 text-xs text-muted-foreground">
-        The recommended model is shown as the default suggestion in model
-        selection dropdowns throughout the platform.
-      </p>
-
-      <div className="flex items-center gap-3">
-        <select
-          value={selectedModelId}
-          onChange={(e) => setSelectedModelId(e.target.value)}
-          className="flex-1 rounded-md border border-input bg-background px-3 py-2 text-sm"
-          disabled={isSaving}
-        >
-          <option value="">-- Select a model --</option>
-          {enabledModels.map((model) => (
-            <option key={model.id} value={model.id}>
-              {model.display_name} ({model.slug})
-            </option>
-          ))}
-        </select>
-
-        <Button
-          type="button"
-          variant="primary"
-          size="small"
-          onClick={handleSave}
-          disabled={!hasChanges || !selectedModelId || isSaving}
-        >
-          {isSaving ? "Saving..." : "Save"}
-        </Button>
-      </div>
-
-      {error && <p className="mt-2 text-xs text-destructive">{error}</p>}
-
-      {currentRecommended && !hasChanges && (
-        <p className="mt-2 text-xs text-muted-foreground">
-          Currently set to:{" "}
-          <span className="font-medium">{currentRecommended.display_name}</span>
-        </p>
-      )}
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/getLlmRegistryPage.ts

@@ -1,46 +0,0 @@
-/**
- * Server-side data fetching for LLM Registry page.
- */
-
-import {
-  fetchLlmCreators,
-  fetchLlmMigrations,
-  fetchLlmModels,
-  fetchLlmProviders,
-} from "./actions";
-
-export async function getLlmRegistryPageData() {
-  // Fetch providers and models (required)
-  const [providersResponse, modelsResponse] = await Promise.all([
-    fetchLlmProviders(),
-    fetchLlmModels(),
-  ]);
-
-  // Fetch migrations separately with fallback (table might not exist yet)
-  let migrations: Awaited<ReturnType<typeof fetchLlmMigrations>>["migrations"] =
-    [];
-  try {
-    const migrationsResponse = await fetchLlmMigrations(false);
-    migrations = migrationsResponse.migrations;
-  } catch {
-    // Migrations table might not exist yet - that's ok, just show empty list
-    console.warn("Could not fetch migrations - table may not exist yet");
-  }
-
-  // Fetch creators separately with fallback (table might not exist yet)
-  let creators: Awaited<ReturnType<typeof fetchLlmCreators>>["creators"] = [];
-  try {
-    const creatorsResponse = await fetchLlmCreators();
-    creators = creatorsResponse.creators;
-  } catch {
-    // Creators table might not exist yet - that's ok, just show empty list
-    console.warn("Could not fetch creators - table may not exist yet");
-  }
-
-  return {
-    providers: providersResponse.providers,
-    models: modelsResponse.models,
-    migrations,
-    creators,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/admin/llms/page.tsx

@@ -1,14 +0,0 @@
-import { withRoleAccess } from "@/lib/withRoleAccess";
-import { getLlmRegistryPageData } from "./getLlmRegistryPage";
-import { LlmRegistryDashboard } from "./components/LlmRegistryDashboard";
-
-async function LlmRegistryPage() {
-  const data = await getLlmRegistryPageData();
-  return <LlmRegistryDashboard {...data} />;
-}
-
-export default async function AdminLlmRegistryPage() {
-  const withAdminAccess = await withRoleAccess(["admin"]);
-  const ProtectedLlmRegistryPage = await withAdminAccess(LlmRegistryPage);
-  return <ProtectedLlmRegistryPage />;
-}

autogpt_platform/frontend/src/app/(platform)/build/components/NewControlPanel/NewBlockMenu/AllBlocksContent/useAllBlockContent.tsx

@@ -7,9 +7,8 @@ import { BlockCategoryResponse } from "@/app/api/__generated__/models/blockCateg
 import { BlockResponse } from "@/app/api/__generated__/models/blockResponse";
 import * as Sentry from "@sentry/nextjs";
 import { getQueryClient } from "@/lib/react-query/queryClient";
-import { useState, useEffect } from "react";
+import { useState } from "react";
 import { useToast } from "@/components/molecules/Toast/use-toast";
-import BackendApi from "@/lib/autogpt-server-api";
 
 export const useAllBlockContent = () => {
   const { toast } = useToast();
@@ -94,32 +93,6 @@ export const useAllBlockContent = () => {
   const isErrorOnLoadingMore = (categoryName: string) =>
     errorLoadingCategories.has(categoryName);
 
-  // Listen for LLM registry refresh notifications
-  useEffect(() => {
-    const api = new BackendApi();
-    const queryClient = getQueryClient();
-
-    const handleNotification = (notification: any) => {
-      if (
-        notification?.type === "LLM_REGISTRY_REFRESH" ||
-        notification?.event === "registry_updated"
-      ) {
-        // Invalidate all block-related queries to force refresh
-        const categoriesQueryKey = getGetV2GetBuilderBlockCategoriesQueryKey();
-        queryClient.invalidateQueries({ queryKey: categoriesQueryKey });
-      }
-    };
-
-    const unsubscribe = api.onWebSocketMessage(
-      "notification",
-      handleNotification,
-    );
-
-    return () => {
-      unsubscribe();
-    };
-  }, []);
-
   return {
     data,
     isLoading,

autogpt_platform/frontend/src/app/(platform)/build/components/legacy-builder/NodeInputs.tsx

@@ -610,11 +610,8 @@ const NodeOneOfDiscriminatorField: FC<{
 
     return oneOfVariants
       .map((variant) => {
-        const discProperty = variant.properties?.[discriminatorProperty];
-        const variantDiscValue =
-          discProperty && "const" in discProperty
-            ? (discProperty.const as string)
-            : undefined; // NOTE: can discriminators only be strings?
+        const variantDiscValue = variant.properties?.[discriminatorProperty]
+          ?.const as string; // NOTE: can discriminators only be strings?
 
         return {
           value: variantDiscValue,
@@ -1127,47 +1124,9 @@ const NodeStringInput: FC<{
   displayName,
 }) => {
   value ||= schema.default || "";
-
-  // Check if we have options with labels (e.g., LLM model picker)
-  const hasOptions = schema.options && schema.options.length > 0;
-  const hasEnum = schema.enum && schema.enum.length > 0;
-
-  // Helper to get display label for a value
-  const getDisplayLabel = (val: string) => {
-    if (hasOptions) {
-      const option = schema.options!.find((opt) => opt.value === val);
-      return option?.label || beautifyString(val);
-    }
-    return beautifyString(val);
-  };
-
   return (
     <div className={className}>
-      {hasOptions ? (
-        // Render options with proper labels (used by LLM model picker)
-        <Select
-          defaultValue={value}
-          onValueChange={(newValue) => handleInputChange(selfKey, newValue)}
-        >
-          <SelectTrigger>
-            <SelectValue placeholder={schema.placeholder || displayName}>
-              {value ? getDisplayLabel(value) : undefined}
-            </SelectValue>
-          </SelectTrigger>
-          <SelectContent className="nodrag">
-            {schema.options!.map((option, index) => (
-              <SelectItem
-                key={index}
-                value={option.value}
-                title={option.description}
-              >
-                {option.label || beautifyString(option.value)}
-              </SelectItem>
-            ))}
-          </SelectContent>
-        </Select>
-      ) : hasEnum ? (
-        // Fallback to enum with beautified strings
+      {schema.enum && schema.enum.length > 0 ? (
         <Select
           defaultValue={value}
           onValueChange={(newValue) => handleInputChange(selfKey, newValue)}
@@ -1176,8 +1135,8 @@ const NodeStringInput: FC<{
             <SelectValue placeholder={schema.placeholder || displayName} />
           </SelectTrigger>
           <SelectContent className="nodrag">
-            {schema
-              .enum!.filter((option) => option)
+            {schema.enum
+              .filter((option) => option)
               .map((option, index) => (
                 <SelectItem key={index} value={option}>
                   {beautifyString(option)}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/ChatMessagesContainer.tsx

@@ -15,6 +15,10 @@ import { ToolUIPart, UIDataTypes, UIMessage, UITools } from "ai";
 import { useEffect, useRef, useState } from "react";
 import { CreateAgentTool } from "../../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../../tools/EditAgent/EditAgent";
+import {
+  CreateFeatureRequestTool,
+  SearchFeatureRequestsTool,
+} from "../../tools/FeatureRequests/FeatureRequests";
 import { FindAgentsTool } from "../../tools/FindAgents/FindAgents";
 import { FindBlocksTool } from "../../tools/FindBlocks/FindBlocks";
 import { RunAgentTool } from "../../tools/RunAgent/RunAgent";
@@ -254,6 +258,20 @@ export const ChatMessagesContainer = ({
                           part={part as ToolUIPart}
                         />
                       );
+                    case "tool-search_feature_requests":
+                      return (
+                        <SearchFeatureRequestsTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-create_feature_request":
+                      return (
+                        <CreateFeatureRequestTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
                     default:
                       return null;
                   }

autogpt_platform/frontend/src/app/(platform)/copilot/styleguide/page.tsx

@@ -14,6 +14,10 @@ import { Text } from "@/components/atoms/Text/Text";
 import { CopilotChatActionsProvider } from "../components/CopilotChatActionsProvider/CopilotChatActionsProvider";
 import { CreateAgentTool } from "../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../tools/EditAgent/EditAgent";
+import {
+  CreateFeatureRequestTool,
+  SearchFeatureRequestsTool,
+} from "../tools/FeatureRequests/FeatureRequests";
 import { FindAgentsTool } from "../tools/FindAgents/FindAgents";
 import { FindBlocksTool } from "../tools/FindBlocks/FindBlocks";
 import { RunAgentTool } from "../tools/RunAgent/RunAgent";
@@ -45,6 +49,8 @@ const SECTIONS = [
   "Tool: Create Agent",
   "Tool: Edit Agent",
   "Tool: View Agent Output",
+  "Tool: Search Feature Requests",
+  "Tool: Create Feature Request",
   "Full Conversation Example",
 ] as const;
 
@@ -1421,6 +1427,235 @@ export default function StyleguidePage() {
               </SubSection>
             </Section>
 
+            {/* ============================================================= */}
+            {/* SEARCH FEATURE REQUESTS                                        */}
+            {/* ============================================================= */}
+
+            <Section title="Tool: Search Feature Requests">
+              <SubSection label="Input streaming">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "input-streaming",
+                    input: { query: "dark mode" },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Input available">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "input-available",
+                    input: { query: "dark mode" },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (with results)">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: { query: "dark mode" },
+                    output: {
+                      type: "feature_request_search",
+                      message:
+                        'Found 2 feature request(s) matching "dark mode".',
+                      query: "dark mode",
+                      count: 2,
+                      results: [
+                        {
+                          id: "fr-001",
+                          identifier: "INT-42",
+                          title: "Add dark mode to the platform",
+                          description:
+                            "Users have requested a dark mode option for the builder and copilot interfaces to reduce eye strain during long sessions.",
+                        },
+                        {
+                          id: "fr-002",
+                          identifier: "INT-87",
+                          title: "Dark theme for agent output viewer",
+                          description:
+                            "Specifically requesting dark theme support for the agent output/execution viewer panel.",
+                        },
+                      ],
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (no results)">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: { query: "teleportation" },
+                    output: {
+                      type: "no_results",
+                      message:
+                        "No feature requests found matching 'teleportation'.",
+                      suggestions: [
+                        "Try different keywords",
+                        "Use broader search terms",
+                        "You can create a new feature request if none exists",
+                      ],
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (error)">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: { query: "dark mode" },
+                    output: {
+                      type: "error",
+                      message: "Failed to search feature requests.",
+                      error: "LINEAR_API_KEY environment variable is not set",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output error">
+                <SearchFeatureRequestsTool
+                  part={{
+                    type: "tool-search_feature_requests",
+                    toolCallId: uid(),
+                    state: "output-error",
+                    input: { query: "dark mode" },
+                  }}
+                />
+              </SubSection>
+            </Section>
+
+            {/* ============================================================= */}
+            {/* CREATE FEATURE REQUEST                                         */}
+            {/* ============================================================= */}
+
+            <Section title="Tool: Create Feature Request">
+              <SubSection label="Input streaming">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "input-streaming",
+                    input: {
+                      title: "Add dark mode",
+                      description: "I would love dark mode for the platform.",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Input available">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "input-available",
+                    input: {
+                      title: "Add dark mode",
+                      description: "I would love dark mode for the platform.",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (new issue created)">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: {
+                      title: "Add dark mode",
+                      description: "I would love dark mode for the platform.",
+                    },
+                    output: {
+                      type: "feature_request_created",
+                      message:
+                        "Created new feature request [INT-105] Add dark mode.",
+                      issue_id: "issue-new-123",
+                      issue_identifier: "INT-105",
+                      issue_title: "Add dark mode",
+                      issue_url:
+                        "https://linear.app/autogpt/issue/INT-105/add-dark-mode",
+                      is_new_issue: true,
+                      customer_name: "user-abc-123",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (added to existing issue)">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: {
+                      title: "Dark mode support",
+                      description:
+                        "Please add dark mode, it would help with long sessions.",
+                      existing_issue_id: "fr-001",
+                    },
+                    output: {
+                      type: "feature_request_created",
+                      message:
+                        "Added your request to existing feature request [INT-42] Add dark mode to the platform.",
+                      issue_id: "fr-001",
+                      issue_identifier: "INT-42",
+                      issue_title: "Add dark mode to the platform",
+                      issue_url:
+                        "https://linear.app/autogpt/issue/INT-42/add-dark-mode-to-the-platform",
+                      is_new_issue: false,
+                      customer_name: "user-xyz-789",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output available (error)">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "output-available",
+                    input: {
+                      title: "Add dark mode",
+                      description: "I would love dark mode.",
+                    },
+                    output: {
+                      type: "error",
+                      message:
+                        "Failed to attach customer need to the feature request.",
+                      error: "Linear API request failed (500): Internal error",
+                    },
+                  }}
+                />
+              </SubSection>
+
+              <SubSection label="Output error">
+                <CreateFeatureRequestTool
+                  part={{
+                    type: "tool-create_feature_request",
+                    toolCallId: uid(),
+                    state: "output-error",
+                    input: { title: "Add dark mode" },
+                  }}
+                />
+              </SubSection>
+            </Section>
+
             {/* ============================================================= */}
             {/* FULL CONVERSATION EXAMPLE                                      */}
             {/* ============================================================= */}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FeatureRequests/FeatureRequests.tsx

@@ -0,0 +1,227 @@
+"use client";
+
+import type { ToolUIPart } from "ai";
+import { useMemo } from "react";
+
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import {
+  ContentBadge,
+  ContentCard,
+  ContentCardDescription,
+  ContentCardHeader,
+  ContentCardTitle,
+  ContentGrid,
+  ContentMessage,
+  ContentSuggestionsList,
+} from "../../components/ToolAccordion/AccordionContent";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import {
+  AccordionIcon,
+  getAccordionTitle,
+  getAnimationText,
+  getFeatureRequestOutput,
+  isCreatedOutput,
+  isErrorOutput,
+  isNoResultsOutput,
+  isSearchResultsOutput,
+  ToolIcon,
+  type FeatureRequestToolType,
+} from "./helpers";
+
+export interface FeatureRequestToolPart {
+  type: FeatureRequestToolType;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: FeatureRequestToolPart;
+}
+
+function truncate(text: string, maxChars: number): string {
+  const trimmed = text.trim();
+  if (trimmed.length <= maxChars) return trimmed;
+  return `${trimmed.slice(0, maxChars).trimEnd()}…`;
+}
+
+export function SearchFeatureRequestsTool({ part }: Props) {
+  const output = getFeatureRequestOutput(part);
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+
+  const normalized = useMemo(() => {
+    if (!output) return null;
+    return { title: getAccordionTitle(part.type, output) };
+  }, [output, part.type]);
+
+  const isOutputAvailable = part.state === "output-available" && !!output;
+
+  const searchOutput =
+    isOutputAvailable && output && isSearchResultsOutput(output)
+      ? output
+      : null;
+  const noResultsOutput =
+    isOutputAvailable && output && isNoResultsOutput(output) ? output : null;
+  const errorOutput =
+    isOutputAvailable && output && isErrorOutput(output) ? output : null;
+
+  const hasExpandableContent =
+    isOutputAvailable &&
+    ((!!searchOutput && searchOutput.count > 0) ||
+      !!noResultsOutput ||
+      !!errorOutput);
+
+  const accordionDescription =
+    hasExpandableContent && searchOutput
+      ? `Found ${searchOutput.count} result${searchOutput.count === 1 ? "" : "s"} for "${searchOutput.query}"`
+      : hasExpandableContent && (noResultsOutput || errorOutput)
+        ? ((noResultsOutput ?? errorOutput)?.message ?? null)
+        : null;
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon
+          toolType={part.type}
+          isStreaming={isStreaming}
+          isError={isError}
+        />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && normalized && (
+        <ToolAccordion
+          icon={<AccordionIcon toolType={part.type} />}
+          title={normalized.title}
+          description={accordionDescription}
+        >
+          {searchOutput && (
+            <ContentGrid>
+              {searchOutput.results.map((r) => (
+                <ContentCard key={r.id}>
+                  <ContentCardHeader>
+                    <ContentCardTitle>{r.title}</ContentCardTitle>
+                  </ContentCardHeader>
+                  {r.description && (
+                    <ContentCardDescription>
+                      {truncate(r.description, 200)}
+                    </ContentCardDescription>
+                  )}
+                </ContentCard>
+              ))}
+            </ContentGrid>
+          )}
+
+          {noResultsOutput && (
+            <div>
+              <ContentMessage>{noResultsOutput.message}</ContentMessage>
+              {noResultsOutput.suggestions &&
+                noResultsOutput.suggestions.length > 0 && (
+                  <ContentSuggestionsList items={noResultsOutput.suggestions} />
+                )}
+            </div>
+          )}
+
+          {errorOutput && (
+            <div>
+              <ContentMessage>{errorOutput.message}</ContentMessage>
+              {errorOutput.error && (
+                <ContentCardDescription>
+                  {errorOutput.error}
+                </ContentCardDescription>
+              )}
+            </div>
+          )}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}
+
+export function CreateFeatureRequestTool({ part }: Props) {
+  const output = getFeatureRequestOutput(part);
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+
+  const normalized = useMemo(() => {
+    if (!output) return null;
+    return { title: getAccordionTitle(part.type, output) };
+  }, [output, part.type]);
+
+  const isOutputAvailable = part.state === "output-available" && !!output;
+
+  const createdOutput =
+    isOutputAvailable && output && isCreatedOutput(output) ? output : null;
+  const errorOutput =
+    isOutputAvailable && output && isErrorOutput(output) ? output : null;
+
+  const hasExpandableContent =
+    isOutputAvailable && (!!createdOutput || !!errorOutput);
+
+  const accordionDescription =
+    hasExpandableContent && createdOutput
+      ? createdOutput.issue_title
+      : hasExpandableContent && errorOutput
+        ? errorOutput.message
+        : null;
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon
+          toolType={part.type}
+          isStreaming={isStreaming}
+          isError={isError}
+        />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && normalized && (
+        <ToolAccordion
+          icon={<AccordionIcon toolType={part.type} />}
+          title={normalized.title}
+          description={accordionDescription}
+        >
+          {createdOutput && (
+            <ContentCard>
+              <ContentCardHeader>
+                <ContentCardTitle>{createdOutput.issue_title}</ContentCardTitle>
+              </ContentCardHeader>
+              <div className="mt-2 flex items-center gap-2">
+                <ContentBadge>
+                  {createdOutput.is_new_issue ? "New" : "Existing"}
+                </ContentBadge>
+              </div>
+              <ContentMessage>{createdOutput.message}</ContentMessage>
+            </ContentCard>
+          )}
+
+          {errorOutput && (
+            <div>
+              <ContentMessage>{errorOutput.message}</ContentMessage>
+              {errorOutput.error && (
+                <ContentCardDescription>
+                  {errorOutput.error}
+                </ContentCardDescription>
+              )}
+            </div>
+          )}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FeatureRequests/helpers.tsx

@@ -0,0 +1,271 @@
+import {
+  CheckCircleIcon,
+  LightbulbIcon,
+  MagnifyingGlassIcon,
+  PlusCircleIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+
+/* ------------------------------------------------------------------ */
+/*  Types (local until API client is regenerated)                      */
+/* ------------------------------------------------------------------ */
+
+interface FeatureRequestInfo {
+  id: string;
+  identifier: string;
+  title: string;
+  description?: string | null;
+}
+
+export interface FeatureRequestSearchResponse {
+  type: "feature_request_search";
+  message: string;
+  results: FeatureRequestInfo[];
+  count: number;
+  query: string;
+}
+
+export interface FeatureRequestCreatedResponse {
+  type: "feature_request_created";
+  message: string;
+  issue_id: string;
+  issue_identifier: string;
+  issue_title: string;
+  issue_url: string;
+  is_new_issue: boolean;
+  customer_name: string;
+}
+
+interface NoResultsResponse {
+  type: "no_results";
+  message: string;
+  suggestions?: string[];
+}
+
+interface ErrorResponse {
+  type: "error";
+  message: string;
+  error?: string;
+}
+
+export type FeatureRequestOutput =
+  | FeatureRequestSearchResponse
+  | FeatureRequestCreatedResponse
+  | NoResultsResponse
+  | ErrorResponse;
+
+export type FeatureRequestToolType =
+  | "tool-search_feature_requests"
+  | "tool-create_feature_request"
+  | string;
+
+/* ------------------------------------------------------------------ */
+/*  Output parsing                                                     */
+/* ------------------------------------------------------------------ */
+
+function parseOutput(output: unknown): FeatureRequestOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (
+      type === "feature_request_search" ||
+      type === "feature_request_created" ||
+      type === "no_results" ||
+      type === "error"
+    ) {
+      return output as FeatureRequestOutput;
+    }
+    // Fallback structural checks
+    if ("results" in output && "query" in output)
+      return output as FeatureRequestSearchResponse;
+    if ("issue_identifier" in output)
+      return output as FeatureRequestCreatedResponse;
+    if ("suggestions" in output && !("error" in output))
+      return output as NoResultsResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+  }
+  return null;
+}
+
+export function getFeatureRequestOutput(
+  part: unknown,
+): FeatureRequestOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+/* ------------------------------------------------------------------ */
+/*  Type guards                                                        */
+/* ------------------------------------------------------------------ */
+
+export function isSearchResultsOutput(
+  output: FeatureRequestOutput,
+): output is FeatureRequestSearchResponse {
+  return (
+    output.type === "feature_request_search" ||
+    ("results" in output && "query" in output)
+  );
+}
+
+export function isCreatedOutput(
+  output: FeatureRequestOutput,
+): output is FeatureRequestCreatedResponse {
+  return (
+    output.type === "feature_request_created" || "issue_identifier" in output
+  );
+}
+
+export function isNoResultsOutput(
+  output: FeatureRequestOutput,
+): output is NoResultsResponse {
+  return (
+    output.type === "no_results" ||
+    ("suggestions" in output && !("error" in output))
+  );
+}
+
+export function isErrorOutput(
+  output: FeatureRequestOutput,
+): output is ErrorResponse {
+  return output.type === "error" || "error" in output;
+}
+
+/* ------------------------------------------------------------------ */
+/*  Accordion metadata                                                 */
+/* ------------------------------------------------------------------ */
+
+export function getAccordionTitle(
+  toolType: FeatureRequestToolType,
+  output: FeatureRequestOutput,
+): string {
+  if (toolType === "tool-search_feature_requests") {
+    if (isSearchResultsOutput(output)) return "Feature requests";
+    if (isNoResultsOutput(output)) return "No feature requests found";
+    return "Feature request search error";
+  }
+  if (isCreatedOutput(output)) {
+    return output.is_new_issue
+      ? "Feature request created"
+      : "Added to feature request";
+  }
+  if (isErrorOutput(output)) return "Feature request error";
+  return "Feature request";
+}
+
+/* ------------------------------------------------------------------ */
+/*  Animation text                                                     */
+/* ------------------------------------------------------------------ */
+
+interface AnimationPart {
+  type: FeatureRequestToolType;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+export function getAnimationText(part: AnimationPart): string {
+  if (part.type === "tool-search_feature_requests") {
+    const query = (part.input as { query?: string } | undefined)?.query?.trim();
+    const queryText = query ? ` for "${query}"` : "";
+
+    switch (part.state) {
+      case "input-streaming":
+      case "input-available":
+        return `Searching feature requests${queryText}`;
+      case "output-available": {
+        const output = parseOutput(part.output);
+        if (!output) return `Searching feature requests${queryText}`;
+        if (isSearchResultsOutput(output)) {
+          return `Found ${output.count} feature request${output.count === 1 ? "" : "s"}${queryText}`;
+        }
+        if (isNoResultsOutput(output))
+          return `No feature requests found${queryText}`;
+        return `Error searching feature requests${queryText}`;
+      }
+      case "output-error":
+        return `Error searching feature requests${queryText}`;
+      default:
+        return "Searching feature requests";
+    }
+  }
+
+  // create_feature_request
+  const title = (part.input as { title?: string } | undefined)?.title?.trim();
+  const titleText = title ? ` "${title}"` : "";
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return `Creating feature request${titleText}`;
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) return `Creating feature request${titleText}`;
+      if (isCreatedOutput(output)) {
+        return output.is_new_issue
+          ? "Feature request created"
+          : "Added to existing feature request";
+      }
+      if (isErrorOutput(output)) return "Error creating feature request";
+      return `Created feature request${titleText}`;
+    }
+    case "output-error":
+      return "Error creating feature request";
+    default:
+      return "Creating feature request";
+  }
+}
+
+/* ------------------------------------------------------------------ */
+/*  Icons                                                              */
+/* ------------------------------------------------------------------ */
+
+export function ToolIcon({
+  toolType,
+  isStreaming,
+  isError,
+}: {
+  toolType: FeatureRequestToolType;
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  const IconComponent =
+    toolType === "tool-create_feature_request"
+      ? PlusCircleIcon
+      : MagnifyingGlassIcon;
+
+  return (
+    <IconComponent
+      size={14}
+      weight="regular"
+      className={
+        isError
+          ? "text-red-500"
+          : isStreaming
+            ? "text-neutral-500"
+            : "text-neutral-400"
+      }
+    />
+  );
+}
+
+export function AccordionIcon({
+  toolType,
+}: {
+  toolType: FeatureRequestToolType;
+}) {
+  const IconComponent =
+    toolType === "tool-create_feature_request"
+      ? CheckCircleIcon
+      : LightbulbIcon;
+  return <IconComponent size={32} weight="light" />;
+}

autogpt_platform/frontend/src/components/atoms/Table/Table.tsx

@@ -1,123 +0,0 @@
-import * as React from "react";
-
-import { cn } from "@/lib/utils";
-
-const Table = React.forwardRef<
-  HTMLTableElement,
-  React.HTMLAttributes<HTMLTableElement>
->(({ className, ...props }, ref) => (
-  <div className="relative w-full overflow-auto">
-    <table
-      ref={ref}
-      className={cn("w-full caption-bottom text-sm", className)}
-      {...props}
-    />
-  </div>
-));
-Table.displayName = "Table";
-
-const TableHeader = React.forwardRef<
-  HTMLTableSectionElement,
-  React.HTMLAttributes<HTMLTableSectionElement>
->(({ className, ...props }, ref) => (
-  <thead ref={ref} className={cn("[&_tr]:border-b", className)} {...props} />
-));
-TableHeader.displayName = "TableHeader";
-
-const TableBody = React.forwardRef<
-  HTMLTableSectionElement,
-  React.HTMLAttributes<HTMLTableSectionElement>
->(({ className, ...props }, ref) => (
-  <tbody
-    ref={ref}
-    className={cn("[&_tr:last-child]:border-0", className)}
-    {...props}
-  />
-));
-TableBody.displayName = "TableBody";
-
-const TableFooter = React.forwardRef<
-  HTMLTableSectionElement,
-  React.HTMLAttributes<HTMLTableSectionElement>
->(({ className, ...props }, ref) => (
-  <tfoot
-    ref={ref}
-    className={cn(
-      "border-t bg-neutral-100/50 font-medium dark:bg-neutral-800/50 [&>tr]:last:border-b-0",
-      className,
-    )}
-    {...props}
-  />
-));
-TableFooter.displayName = "TableFooter";
-
-const TableRow = React.forwardRef<
-  HTMLTableRowElement,
-  React.HTMLAttributes<HTMLTableRowElement>
->(({ className, ...props }, ref) => (
-  <tr
-    ref={ref}
-    className={cn(
-      "border-b transition-colors data-[state=selected]:bg-neutral-100 hover:bg-neutral-100/50 dark:data-[state=selected]:bg-neutral-800 dark:hover:bg-neutral-800/50",
-      className,
-    )}
-    {...props}
-  />
-));
-TableRow.displayName = "TableRow";
-
-const TableHead = React.forwardRef<
-  HTMLTableCellElement,
-  React.ThHTMLAttributes<HTMLTableCellElement>
->(({ className, ...props }, ref) => (
-  <th
-    ref={ref}
-    className={cn(
-      "h-10 px-2 text-left align-middle font-medium text-neutral-500 dark:text-neutral-400 [&:has([role=checkbox])]:pr-0 [&>[role=checkbox]]:translate-y-[2px]",
-      className,
-    )}
-    {...props}
-  />
-));
-TableHead.displayName = "TableHead";
-
-const TableCell = React.forwardRef<
-  HTMLTableCellElement,
-  React.TdHTMLAttributes<HTMLTableCellElement>
->(({ className, ...props }, ref) => (
-  <td
-    ref={ref}
-    className={cn(
-      "p-2 align-middle [&:has([role=checkbox])]:pr-0 [&>[role=checkbox]]:translate-y-[2px]",
-      className,
-    )}
-    {...props}
-  />
-));
-TableCell.displayName = "TableCell";
-
-const TableCaption = React.forwardRef<
-  HTMLTableCaptionElement,
-  React.HTMLAttributes<HTMLTableCaptionElement>
->(({ className, ...props }, ref) => (
-  <caption
-    ref={ref}
-    className={cn(
-      "mt-4 text-sm text-neutral-500 dark:text-neutral-400",
-      className,
-    )}
-    {...props}
-  />
-));
-TableCaption.displayName = "TableCaption";
-
-export {
-  Table,
-  TableHeader,
-  TableBody,
-  TableFooter,
-  TableHead,
-  TableRow,
-  TableCell,
-  TableCaption,
-};

autogpt_platform/frontend/src/components/molecules/Table/Table.tsx

@@ -6,7 +6,7 @@ import {
   TableHead,
   TableHeader,
   TableRow,
-} from "@/components/atoms/Table/Table";
+} from "@/components/__legacy__/ui/table";
 import { Button } from "@/components/atoms/Button/Button";
 import { Input } from "@/components/atoms/Input/Input";
 import { Text } from "@/components/atoms/Text/Text";

autogpt_platform/frontend/src/components/renderers/InputRenderer/utils/input-schema-pre-processor.ts

@@ -1,19 +1,8 @@
 import { RJSFSchema } from "@rjsf/utils";
 
-/**
- * Options type for fields with label/value pairs (e.g., LLM model picker)
- */
-type SchemaOption = {
-  label: string;
-  value: string;
-  group?: string;
-  description?: string;
-};
-
 /**
  * Pre-processes the input schema to ensure all properties have a type defined.
  * If a property doesn't have a type, it assigns a union of all supported JSON Schema types.
- * Also converts custom 'options' array to RJSF's enum/enumNames format.
  */
 
 export function preprocessInputSchema(schema: RJSFSchema): RJSFSchema {
@@ -31,20 +20,6 @@ export function preprocessInputSchema(schema: RJSFSchema): RJSFSchema {
       if (property && typeof property === "object") {
         const processedProperty = { ...property };
 
-        // Convert custom 'options' array to RJSF's enum/enumNames format
-        // This enables proper label display for dropdowns like the LLM model picker
-        if (
-          (processedProperty as any).options &&
-          Array.isArray((processedProperty as any).options) &&
-          (processedProperty as any).options.length > 0
-        ) {
-          const options = (processedProperty as any).options as SchemaOption[];
-          processedProperty.enum = options.map((opt) => opt.value);
-          (processedProperty as any).enumNames = options.map(
-            (opt) => opt.label,
-          );
-        }
-
         // Only add type if no type is defined AND no anyOf/oneOf/allOf is present
         if (
           !processedProperty.type &&

autogpt_platform/frontend/src/hooks/useAgentGraph.tsx

@@ -77,45 +77,17 @@ export default function useAgentGraph(
 
   // Load available blocks & flows (stable - only loads once)
   useEffect(() => {
-    const loadBlocks = () => {
-      api
-        .getBlocks()
-        .then((blocks) => {
-          setAllBlocks(blocks);
-        })
-        .catch();
-    };
+    api
+      .getBlocks()
+      .then((blocks) => {
+        setAllBlocks(blocks);
+      })
+      .catch();
 
-    const loadFlows = () => {
-      api
-        .listGraphs()
-        .then((flows) => setAvailableFlows(flows))
-        .catch();
-    };
-
-    // Initial load
-    loadBlocks();
-    loadFlows();
-
-    // Listen for LLM registry refresh notifications to reload blocks
-    const deregisterRegistryRefresh = api.onWebSocketMessage(
-      "notification",
-      (notification) => {
-        if (
-          notification?.type === "LLM_REGISTRY_REFRESH" ||
-          notification?.event === "registry_updated"
-        ) {
-          console.log(
-            "Received LLM registry refresh notification, reloading blocks...",
-          );
-          loadBlocks();
-        }
-      },
-    );
-
-    return () => {
-      deregisterRegistryRefresh();
-    };
+    api
+      .listGraphs()
+      .then((flows) => setAvailableFlows(flows))
+      .catch();
   }, [api]);
 
   // Subscribe to execution events

autogpt_platform/frontend/src/lib/autogpt-server-api/types.ts

@@ -186,7 +186,6 @@ export type BlockIOStringSubSchema = BlockIOSubSchemaMeta & {
   default?: string;
   format?: string;
   maxLength?: number;
-  options?: { value: string; label: string; description?: string }[];
 };
 
 export type BlockIONumberSubSchema = BlockIOSubSchemaMeta & {

autogpt_platform/frontend/src/lib/utils.ts

@@ -285,20 +285,17 @@ export function fillObjectDefaultsFromSchema(
       // Apply simple default values
       obj[key] ??= propertySchema.default;
     } else if (
-      "type" in propertySchema &&
       propertySchema.type === "object" &&
       "properties" in propertySchema
     ) {
       // Recursively fill defaults for nested objects
       obj[key] = fillObjectDefaultsFromSchema(obj[key] ?? {}, propertySchema);
-    } else if ("type" in propertySchema && propertySchema.type === "array") {
+    } else if (propertySchema.type === "array") {
       obj[key] ??= [];
       // If the array items are objects, fill their defaults as well
       if (
         Array.isArray(obj[key]) &&
-        propertySchema.items &&
-        "type" in propertySchema.items &&
-        propertySchema.items.type === "object" &&
+        propertySchema.items?.type === "object" &&
         "properties" in propertySchema.items
       ) {
         for (const item of obj[key]) {

plans/SECRT-1950-claude-ci-optimizations.md

@@ -0,0 +1,165 @@
+# Implementation Plan: SECRT-1950 - Apply E2E CI Optimizations to Claude Code Workflows
+
+## Ticket
+[SECRT-1950](https://linear.app/autogpt/issue/SECRT-1950)
+
+## Summary
+Apply Pwuts's CI performance optimizations from PR #12090 to Claude Code workflows.
+
+## Reference PR
+https://github.com/Significant-Gravitas/AutoGPT/pull/12090
+
+---
+
+## Analysis
+
+### Current State (claude.yml)
+
+**pnpm caching (lines 104-118):**
+```yaml
+- name: Set up Node.js
+  uses: actions/setup-node@v6
+  with:
+    node-version: "22"
+
+- name: Enable corepack
+  run: corepack enable
+
+- name: Set pnpm store directory
+  run: |
+    pnpm config set store-dir ~/.pnpm-store
+    echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
+
+- name: Cache frontend dependencies
+  uses: actions/cache@v5
+  with:
+    path: ~/.pnpm-store
+    key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
+    restore-keys: |
+      ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+      ${{ runner.os }}-pnpm-
+```
+
+**Docker setup (lines 134-165):**
+- Uses `docker-buildx-action@v3` 
+- Has manual Docker image caching via `actions/cache`
+- Runs `docker compose up` without buildx bake optimization
+
+### Pwuts's Optimizations (PR #12090)
+
+1. **Simplified pnpm caching** - Use `setup-node` built-in cache:
+```yaml
+- name: Enable corepack
+  run: corepack enable
+
+- name: Set up Node
+  uses: actions/setup-node@v6
+  with:
+    node-version: "22.18.0"
+    cache: "pnpm"
+    cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+```
+
+2. **Docker build caching via buildx bake**:
+```yaml
+- name: Set up Docker Buildx
+  uses: docker/setup-buildx-action@v3
+  with:
+    driver: docker-container
+    driver-opts: network=host
+
+- name: Expose GHA cache to docker buildx CLI
+  uses: crazy-max/ghaction-github-runtime@v3
+
+- name: Build Docker images (with cache)
+  run: |
+    pip install pyyaml
+    docker compose -f docker-compose.yml config > docker-compose.resolved.yml
+    python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
+      --source docker-compose.resolved.yml \
+      --cache-from "type=gha" \
+      --cache-to "type=gha,mode=max" \
+      ...
+    docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
+```
+
+---
+
+## Proposed Changes
+
+### 1. Update pnpm caching in `claude.yml`
+
+**Before:**
+- Manual cache key generation
+- Separate `actions/cache` step
+- Manual pnpm store directory config
+
+**After:**
+- Use `setup-node` built-in `cache: "pnpm"` option
+- Remove manual cache step
+- Keep `corepack enable` before `setup-node`
+
+### 2. Update Docker build in `claude.yml`
+
+**Before:**
+- Manual Docker layer caching via `actions/cache` with `/tmp/.buildx-cache`
+- Simple `docker compose build`
+
+**After:**
+- Use `crazy-max/ghaction-github-runtime@v3` to expose GHA cache
+- Use `docker-ci-fix-compose-build-cache.py` script
+- Build with `docker buildx bake`
+
+### 3. Apply same changes to other Claude workflows
+
+- `claude-dependabot.yml` - Check if it has similar patterns
+- `claude-ci-failure-auto-fix.yml` - Check if it has similar patterns
+- `copilot-setup-steps.yml` - Reusable workflow, may be the source of truth
+
+---
+
+## Files to Modify
+
+1. `.github/workflows/claude.yml`
+2. `.github/workflows/claude-dependabot.yml` (if applicable)
+3. `.github/workflows/claude-ci-failure-auto-fix.yml` (if applicable)
+
+## Dependencies
+
+- PR #12090 must be merged first (provides the `docker-ci-fix-compose-build-cache.py` script)
+- Backend Dockerfile optimizations (already in PR #12090)
+
+---
+
+## Test Plan
+
+1. Create PR with changes
+2. Trigger Claude workflow manually or via `@claude` mention on a test issue
+3. Compare CI runtime before/after
+4. Verify Claude agent still works correctly (can checkout, build, run tests)
+
+---
+
+## Risk Assessment
+
+**Low risk:**
+- These are CI infrastructure changes, not code changes
+- If caching fails, builds fall back to uncached (slower but works)
+- Changes mirror proven patterns from PR #12090
+
+---
+
+## Questions for Reviewer
+
+1. Should we wait for PR #12090 to merge before creating this PR?
+2. Does `copilot-setup-steps.yml` need updating, or is it a separate concern?
+3. Any concerns about cache key collisions between frontend E2E and Claude workflows?
+
+---
+
+## Verified
+
+- ✅ **`claude-dependabot.yml`**: Has same pnpm caching pattern as `claude.yml` (manual `actions/cache`) — NEEDS UPDATE
+- ✅ **`claude-ci-failure-auto-fix.yml`**: Simple workflow with no pnpm or Docker caching — NO CHANGES NEEDED
+- ✅ **Script path**: `docker-ci-fix-compose-build-cache.py` will be at `.github/workflows/scripts/` after PR #12090 merges
+- ✅ **Test seed caching**: NOT APPLICABLE — Claude workflows spin up a dev environment but don't run E2E tests with pre-seeded data. The seed caching in PR #12090 is specific to the frontend E2E test suite which needs consistent test data. Claude just needs the services running.