Change AI engine to execute tools in Java instead of on frontend (#6116)

# Description of Changes
Redesign AI engine so that it autogenerates the `tool_models.py` file
from the OpenAPI spec so the Python has access to the Java API
parameters and the full list of Java tools that it can run. CI ensures
that whenever someone modifies a tool endpoint that the AI enigne tool
models get updated as well (the dev gets told to run `task
engine:tool-models`).

There's loads of advantages to having the Java be the one that actually
executes the tools, rather than the frontend as it was previously set up
to theoretically use:
- The AI gets much better descriptions of the params from the API docs
- It'll be usable headless in the future so a Java daemon could run to
execute ops on files in a folder without the need for the UI to run
- The Java already has all the logic it needs to execute the tools 
- We don't need to parse the TypeScript to find the API (which is hard
because the TS wasn't designed to be computer-read to extract the API)

I've also hooked up the prototype frontend to ensure it's working
properly, and have built it in a way that all the tool names can be
translated properly, which was always an issue with previous prototypes
of this.

---------

Co-authored-by: Anthony Stirling <[email protected]>
Co-authored-by: EthanHealy01 <[email protected]>

engine/src/stirling/contracts/agent_specs.py

@@ -4,7 +4,7 @@ from typing import Annotated, Literal
 
 from pydantic import Field
 
-from stirling.models import ApiModel, OperationId
+from stirling.models import ApiModel, ToolEndpoint
 
 from .common import StepKind, ToolOperationStep
 
@@ -13,7 +13,7 @@ class AiToolAgentStep(ApiModel):
     kind: Literal[StepKind.AI_TOOL] = StepKind.AI_TOOL
     title: str
     description: str
-    tool: OperationId
+    tool: ToolEndpoint
     instruction: str
 
 

engine/src/stirling/contracts/common.py

@@ -5,7 +5,7 @@ from typing import Literal, assert_never
 
 from pydantic import Field, model_validator
 
-from stirling.models import OPERATIONS, ApiModel, OperationId
+from stirling.models import OPERATIONS, ApiModel, ToolEndpoint
 from stirling.models.agent_tool_models import AGENT_OPERATIONS, AgentToolId, AnyParamModel, AnyToolId
 
 
@@ -110,7 +110,7 @@ class ToolOperationStep(ApiModel):
     def validate_tool_parameter_pairing(self) -> ToolOperationStep:
         if isinstance(self.tool, AgentToolId):
             expected_type = AGENT_OPERATIONS[self.tool]
-        elif isinstance(self.tool, OperationId):
+        elif isinstance(self.tool, ToolEndpoint):
             expected_type = OPERATIONS[self.tool]
         else:
             assert_never(self.tool)

engine/src/stirling/contracts/execution.py

@@ -4,7 +4,7 @@ from typing import Annotated, Any, Literal
 
 from pydantic import Field
 
-from stirling.models import ApiModel, OperationId, ParamToolModel
+from stirling.models import ApiModel, ParamToolModel, ToolEndpoint
 
 from .agent_specs import AgentSpec
 from .common import WorkflowOutcome
@@ -12,7 +12,7 @@ from .common import WorkflowOutcome
 
 class ExecutionStepResult(ApiModel):
     step_index: int
-    tool: OperationId | None = None
+    tool: ToolEndpoint | None = None
     success: bool
     output_summary: str | None = None
     output_data: dict[str, Any] = Field(default_factory=dict)
@@ -33,7 +33,7 @@ class AgentExecutionRequest(ApiModel):
 
 class ToolCallExecutionAction(ApiModel):
     outcome: Literal[WorkflowOutcome.TOOL_CALL] = WorkflowOutcome.TOOL_CALL
-    tool: OperationId
+    tool: ToolEndpoint
     parameters: ParamToolModel
     rationale: str | None = None