Files
Stirling-PDF/.taskfiles/engine.yml
T
e5767ed58b 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]>
2026-04-20 15:57:11 +01:00

129 lines
2.8 KiB
YAML

version: '3'
tasks:
install:
desc: "Install engine dependencies"
run: once
cmds:
- uv python install 3.13.8
- uv sync
sources:
- uv.lock
- pyproject.toml
status:
- test -d .venv
prepare:
desc: "Set up engine .env from template"
deps: [install]
cmds:
- uv run scripts/setup_env.py
sources:
- scripts/setup_env.py
- config/.env.example
generates:
- .env
run:
desc: "Run engine server"
deps: [prepare]
ignore_error: true
dir: src
env:
PYTHONUNBUFFERED: "1"
cmds:
- uv run uvicorn stirling.api.app:app --host 0.0.0.0 --port 5001
dev:
desc: "Start engine dev server with hot reload"
deps: [prepare]
ignore_error: true
dir: src
env:
PYTHONUNBUFFERED: "1"
cmds:
- uv run uvicorn stirling.api.app:app --host 0.0.0.0 --port 5001 --reload
lint:
desc: "Run linting"
deps: [install]
cmds:
- uv run ruff check .
lint:fix:
desc: "Auto-fix lint issues"
deps: [install]
cmds:
- uv run ruff check . --fix
format:
desc: "Auto-fix code formatting"
deps: [install]
cmds:
- uv run ruff format .
format:check:
desc: "Check code formatting"
deps: [install]
cmds:
- uv run ruff format . --diff
typecheck:
desc: "Run type checking"
deps: [install]
cmds:
- uv run pyright . --warnings
test:
desc: "Run tests"
deps: [prepare]
cmds:
- uv run pytest tests
fix:
desc: "Auto-fix lint + format"
cmds:
- task: lint:fix
- task: format
check:
desc: "Full engine quality gate"
cmds:
- task: typecheck
- task: lint
- task: format:check
- task: test
tool-models:
desc: "Generate tool_models.py from Java OpenAPI spec (SwaggerDoc.json)"
deps: [install, ":backend:swagger"]
cmds:
- uv run python scripts/generate_tool_models.py --spec ../SwaggerDoc.json --output src/stirling/models/tool_models.py
sources:
- ../SwaggerDoc.json
- scripts/generate_tool_models.py
generates:
- src/stirling/models/tool_models.py
clean:
desc: "Clean build artifacts"
cmds:
- task: '{{if eq .OS "Windows_NT"}}clean-windows{{else}}clean-unix{{end}}'
clean-unix:
internal: true
desc: "Clean build artifacts"
cmds:
- rm -rf .venv data logs output
# On Windows, use PowerShell as bash failed to delete some dependencies
clean-windows:
internal: true
desc: "Clean build artifacts"
ignore_error: true
cmds:
- powershell rm -Recurse -Force -ErrorAction SilentlyContinue .venv
- powershell rm -Recurse -Force -ErrorAction SilentlyContinue data
- powershell rm -Recurse -Force -ErrorAction SilentlyContinue logs
- powershell rm -Recurse -Force -ErrorAction SilentlyContinue output