kitaru-evaluator 0.1.0rc0__tar.gz

kitaru_evaluator-0.1.0rc0/.gitignore

@@ -0,0 +1,298 @@
+# iCloud conflict duplicates (pattern: "filename 2.ext" or "filename 2")
+*[[:space:]]2.[!.]*
+*[[:space:]]2
+
+# Helm dependency artifacts (rebuilt via helm dep update)
+helm/charts/
+helm/Chart.lock
+
+# pnpm
+**/.pnpm-store
+
+# macOS
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+plugins/candidate-wheels/*
+!plugins/candidate-wheels/.gitkeep
+downloads/
+eggs/
+.eggs/
+lib/
+!docs/lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Cloudflare local state
+.wrangler/
+
+# Local project markers
+.kitaru/
+.zen/
+
+# Git worktrees (isolated workspaces created via git worktree add)
+.worktrees/
+
+# Design docs + Repoprompt
+design/
+dogfood-output/
+prompt-exports/
+
+# Local Kitaru UI build artifacts (used by docker/Dockerfile.server-dev)
+docker/kitaru-ui-dist/
+
+# MCP
+.mcp.json
+
+# Claude
+**/.claude/settings.local.json
+.claude/*
+!.claude/settings.json
+!.claude/skills/
+
+# Playwright MCP
+.playwright-mcp/
+
+# Bundled Kitaru UI (generated at build time by scripts/download-ui.sh)
+src/kitaru/_ui/dist/
+src/kitaru/_ui/bundle_manifest.json
+.kitaru-ui-bundles/
+
+# Codex
+.codex/*
+!.codex/skills/
+AGENTS.override.md
+.agents/skills/*
+!.agents/skills/kitaru-dev/
+!.agents/skills/kitaru-dev/**
+!.agents/skills/kitaru-docs/
+!.agents/skills/kitaru-docs/**
+!.agents/skills/kitaru-evaluator-authoring/
+!.agents/skills/kitaru-evaluator-authoring/**
+!.agents/skills/kitaru-session-improvement/
+!.agents/skills/kitaru-session-improvement/**
+!.agents/skills/kitaru-tests-release/
+!.agents/skills/kitaru-tests-release/**
+
+# Agent Skills
+.pi/
+.claude/skills/building-pydantic-ai-agents
+.claude/skills/instrumentation
+skills-lock.json
+
+# Local PR review screenshots
+.pr-screenshots/
+
+# Local scratch — single-developer scratch flow files at repo root
+/my_flow.py
+.claude/skills/logfire-instrumentation
+.clawpatch/
+docs/investigations/
+docs/plans/
+docs/reviews/
+plans/
+replay-verify-reports-live/
+replay-verify-reports/
+
+# OpenAPI baseline build output
+openapi/.build/
+
+# Generated by the canonical evaluator-authoring walkthrough
+/examples/pydantic_ai_ticket_resolver/evaluator.py

kitaru_evaluator-0.1.0rc0/CHANGELOG.md

@@ -0,0 +1,5 @@
+# Changelog
+
+## 0.1.0rc0
+
+- Initial release candidate for the built-in evaluator package.

kitaru_evaluator-0.1.0rc0/PKG-INFO

@@ -0,0 +1,7 @@
+Metadata-Version: 2.4
+Name: kitaru-evaluator
+Version: 0.1.0rc0
+Summary: Built-in deterministic evaluators for Kitaru.
+License-Expression: Apache-2.0
+Requires-Python: >=3.11
+Requires-Dist: kitaru<0.23,>=0.22.0rc0

kitaru_evaluator-0.1.0rc0/pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "kitaru-evaluator"
+version = "0.1.0rc0"
+description = "Built-in deterministic evaluators for Kitaru."
+license = "Apache-2.0"
+requires-python = ">=3.11"
+dependencies = ["kitaru>=0.22.0rc0,<0.23"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/kitaru_evaluator"]

kitaru_evaluator-0.1.0rc0/src/kitaru_evaluator/__init__.py

@@ -0,0 +1 @@
+"""Built-in deterministic evaluators for Kitaru."""

kitaru_evaluator-0.1.0rc0/src/kitaru_evaluator/basic.py

@@ -0,0 +1,69 @@
+"""Basic deterministic evaluators."""
+
+from collections import Counter
+
+from kitaru.api_models.v1.evaluation import EvaluationResult
+from kitaru.api_models.v1.session_node import NodeType
+from kitaru.task.evaluator import SessionView
+
+
+def cost(session: SessionView) -> EvaluationResult:
+    """Report the total recorded cost of a session."""
+    recorded_cost = session.session.cost
+    if recorded_cost is None or any(
+        node.node_type is NodeType.LLM_CALL and node.cost is None
+        for node in session.nodes
+    ):
+        return EvaluationResult(
+            name="cost",
+            value="unavailable",
+            explanation="The session has incomplete LLM cost information.",
+        )
+    return EvaluationResult(
+        name="cost",
+        score=float(recorded_cost),
+        explanation=f"The session recorded a total cost of {recorded_cost}.",
+    )
+
+
+def latency(session: SessionView) -> EvaluationResult:
+    """Measure the wall-clock duration of a session in seconds."""
+    started_at = session.session.started_at
+    ended_at = session.session.ended_at
+    if started_at is None or ended_at is None:
+        return EvaluationResult(
+            name="latency_seconds",
+            score=0.0,
+            explanation="The session has no complete timing information.",
+        )
+    duration = max((ended_at - started_at).total_seconds(), 0.0)
+    return EvaluationResult(
+        name="latency_seconds",
+        score=duration,
+        explanation=f"The session ran for {duration:.3f} seconds.",
+    )
+
+
+def tool_call_patterns(session: SessionView) -> EvaluationResult:
+    """Classify whether a session repeats calls to the same tool."""
+    tool_names = [
+        node.tool_name or node.name
+        for node in session.nodes
+        if node.node_type is NodeType.TOOL_CALL
+    ]
+    counts = Counter(tool_names)
+    repeated_calls = sum(count - 1 for count in counts.values() if count > 1)
+    if not tool_names:
+        pattern = "no-tool-calls"
+    elif repeated_calls:
+        pattern = "repeated-tools"
+    else:
+        pattern = "distinct-tools"
+    return EvaluationResult(
+        name="tool_call_pattern",
+        score=float(repeated_calls),
+        value=pattern,
+        explanation=(
+            f"Found {len(tool_names)} tool calls and {repeated_calls} repeated calls."
+        ),
+    )