chore: move all Llama Stack types from llama-models to llama-stack (m…

…eta-llama#1098)

llama-models should have extremely minimal cruft. Its sole purpose
should be didactic -- show the simplest implementation of the llama
models and document the prompt formats, etc.

This PR is the complement to
meta-llama/llama-models#279

## Test Plan

Ensure all `llama` CLI `model` sub-commands work:

```bash
llama model list
llama model download --model-id ...
llama model prompt-format -m ...
```

Ran tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/
LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/
```

Create a fresh venv `uv venv && source .venv/bin/activate` and run
`llama stack build --template fireworks --image-type venv` followed by
`llama stack run together --image-type venv` <-- the server runs

Also checked that the OpenAPI generator can run and there is no change
in the generated files as a result.

```bash
cd docs/openapi_generator
sh run_openapi_generator.sh
```

.pre-commit-config.yaml

@@ -30,6 +30,7 @@ repos:
     rev: v0.9.4
     hooks:
     -   id: ruff
+        exclude: ^llama_stack/strong_typing/.*$
     -   id: ruff-format
 
 -   repo: https://github.com/adamchainz/blacken-docs
@@ -43,7 +44,13 @@ repos:
     rev: 0.5.26
     hooks:
     -   id: uv-export
-        args: ["--frozen", "--no-hashes", "--no-emit-project"]
+        args: [
+            "--frozen", 
+            "--no-hashes", 
+            "--no-emit-project", 
+            "--output-file=requirements.txt"
+        ]
+        files: ^pyproject\.toml$
     -   id: uv-sync
 
 # -   repo: https://github.com/pre-commit/mirrors-mypy

docs/openapi_generator/generate.py

@@ -16,18 +16,6 @@
 import fire
 import ruamel.yaml as yaml
 
-from llama_models import schema_utils
-
-# We do some monkey-patching to ensure our definitions only use the minimal
-# (json_schema_type, webmethod) definitions from the llama_models package. For
-# generation though, we need the full definitions and implementations from the
-#  (json-strong-typing) package.
-
-from .strong_typing.schema import json_schema_type, register_schema
-
-schema_utils.json_schema_type = json_schema_type
-schema_utils.register_schema = register_schema
-
 from llama_stack.apis.version import LLAMA_STACK_API_VERSION  # noqa: E402
 from llama_stack.distribution.stack import LlamaStack  # noqa: E402
 

docs/openapi_generator/pyopenapi/generator.py

@@ -10,25 +10,25 @@
 from dataclasses import make_dataclass
 from typing import Any, Dict, Set, Union
 
-from ..strong_typing.core import JsonType
-from ..strong_typing.docstring import Docstring, parse_type
-from ..strong_typing.inspection import (
+from llama_stack.strong_typing.core import JsonType
+from llama_stack.strong_typing.docstring import Docstring, parse_type
+from llama_stack.strong_typing.inspection import (
     is_generic_list,
     is_type_optional,
     is_type_union,
     unwrap_generic_list,
     unwrap_optional_type,
     unwrap_union_types,
 )
-from ..strong_typing.name import python_type_to_name
-from ..strong_typing.schema import (
+from llama_stack.strong_typing.name import python_type_to_name
+from llama_stack.strong_typing.schema import (
     get_schema_identifier,
     JsonSchemaGenerator,
     register_schema,
     Schema,
     SchemaOptions,
 )
-from ..strong_typing.serialization import json_dump_string, object_to_json
+from llama_stack.strong_typing.serialization import json_dump_string, object_to_json
 
 from .operations import (
     EndpointOperation,

docs/openapi_generator/pyopenapi/operations.py

@@ -15,7 +15,7 @@
 
 from termcolor import colored
 
-from ..strong_typing.inspection import get_signature
+from llama_stack.strong_typing.inspection import get_signature
 
 
 def split_prefix(

docs/openapi_generator/pyopenapi/specification.py

@@ -9,7 +9,7 @@
 from dataclasses import dataclass
 from typing import Any, ClassVar, Dict, List, Optional, Union
 
-from ..strong_typing.schema import JsonType, Schema, StrictJsonType
+from llama_stack.strong_typing.schema import JsonType, Schema, StrictJsonType
 
 URL = str
 

docs/openapi_generator/pyopenapi/utility.py

@@ -9,7 +9,7 @@
 from pathlib import Path
 from typing import TextIO
 
-from ..strong_typing.schema import object_to_json, StrictJsonType
+from llama_stack.strong_typing.schema import object_to_json, StrictJsonType
 
 from .generator import Generator
 from .options import Options

llama_stack/apis/agents/agents.py

@@ -19,7 +19,6 @@
     runtime_checkable,
 )
 
-from llama_models.schema_utils import json_schema_type, register_schema, webmethod
 from pydantic import BaseModel, ConfigDict, Field
 
 from llama_stack.apis.common.content_types import URL, ContentDelta, InterleavedContent
@@ -38,6 +37,7 @@
 from llama_stack.apis.safety import SafetyViolation
 from llama_stack.apis.tools import ToolDef
 from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
+from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 
 class Attachment(BaseModel):

llama_stack/apis/batch_inference/batch_inference.py

@@ -6,7 +6,6 @@
 
 from typing import List, Optional, Protocol, runtime_checkable
 
-from llama_models.schema_utils import json_schema_type, webmethod
 from pydantic import BaseModel
 
 from llama_stack.apis.inference import (
@@ -21,6 +20,7 @@
     ToolDefinition,
     ToolPromptFormat,
 )
+from llama_stack.schema_utils import json_schema_type, webmethod
 
 
 @json_schema_type

llama_stack/apis/benchmarks/benchmarks.py

@@ -5,10 +5,10 @@
 # the root directory of this source tree.
 from typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
 
-from llama_models.schema_utils import json_schema_type, webmethod
 from pydantic import BaseModel, Field
 
 from llama_stack.apis.resource import Resource, ResourceType
+from llama_stack.schema_utils import json_schema_type, webmethod
 
 
 class CommonBenchmarkFields(BaseModel):

llama_stack/apis/common/content_types.py

@@ -7,10 +7,11 @@
 from enum import Enum
 from typing import Annotated, List, Literal, Optional, Union
 
-from llama_models.llama3.api.datatypes import ToolCall
-from llama_models.schema_utils import json_schema_type, register_schema
 from pydantic import BaseModel, Field, model_validator
 
+from llama_stack.models.llama.datatypes import ToolCall
+from llama_stack.schema_utils import json_schema_type, register_schema
+
 
 @json_schema_type
 class URL(BaseModel):

llama_stack/apis/common/deployment_types.py

@@ -7,10 +7,10 @@
 from enum import Enum
 from typing import Any, Dict, Optional
 
-from llama_models.schema_utils import json_schema_type
 from pydantic import BaseModel
 
 from llama_stack.apis.common.content_types import URL
+from llama_stack.schema_utils import json_schema_type
 
 
 @json_schema_type

llama_stack/apis/common/job_types.py

@@ -5,9 +5,10 @@
 # the root directory of this source tree.
 from enum import Enum
 
-from llama_models.schema_utils import json_schema_type
 from pydantic import BaseModel
 
+from llama_stack.schema_utils import json_schema_type
+
 
 @json_schema_type
 class Job(BaseModel):