evalgate-sdk 3.5.0__tar.gz → 3.5.1__tar.gz

{evalgate_sdk-3.5.0 → evalgate_sdk-3.5.1}/CHANGELOG.md

@@ -9,6 +9,15 @@ Version numbering is aligned with the TypeScript SDK (`@evalgate/sdk`) and the p
 
 **Version history note:** The Python SDK jumped from 1.0.0 → 1.9.x → 2.0.0 to stay in sync with the TypeScript SDK. The TypeScript SDK had many releases (1.1–1.9) before the Python SDK existed. We now align both SDKs on the same major.minor version.
 
+## [3.5.1] - 2026-06-26
+
+### Fixed
+- **CLI JSON contracts** — `check --format json` now emits one parseable JSON document.
+- **Zero-config scaffolds** — `start --template` writes config that `run` and `doctor` discover consistently.
+- **Runtime scoring defaults** — boolean/dict executor fallbacks now use the SDK's 0-100 score scale.
+- **Sync safety** — missing labeled datasets surface an explicit error, and prompt pulls write UTF-8 content on Windows.
+- **Default CLI install** — `pip install evalgate-sdk` now includes the runtime dependencies needed for the `evalgate` command.
+
 ## [3.5.0] - 2026-04-09
 
 ### Added

{evalgate_sdk-3.5.0 → evalgate_sdk-3.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: evalgate-sdk
-Version: 3.5.0
+Version: 3.5.1
 Summary: EvalGate Python SDK — CI for AI behavior. Traces, evaluations, assertions, and regression gates for LLM apps.
 Project-URL: Homepage, https://evalgate.com
 Project-URL: Documentation, https://github.com/evalgate/ai-evaluation-platform#readme
@@ -24,6 +24,8 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Requires-Dist: httpx<1,>=0.27
 Requires-Dist: pydantic<3,>=2.0
+Requires-Dist: rich>=13
+Requires-Dist: typer>=0.12
 Provides-Extra: all
 Requires-Dist: anthropic>=0.20; extra == 'all'
 Requires-Dist: langchain-core>=0.2; extra == 'all'
@@ -65,7 +67,6 @@ Use it to run assertions, trace agent workflows, inspect platform runs, orchestr
 
 ```bash
 pip install evalgate-sdk
-pip install "evalgate-sdk[cli]"
 ```
 
 Optional extras:
@@ -125,6 +126,35 @@ evalgate judge registry
 evalgate judge presets
 ```
 
+## Web App Sync
+
+The Python CLI uses the same sync contracts as the TypeScript SDK. Local labeled
+JSONL can be pushed into the web app, web-labeled cases can be merged back into
+the same file, and prompt files can round-trip with stale active-version
+protection.
+
+```bash
+# Push local labels into the web app and pull web labels back into JSONL
+evalgate sync \
+  --project-key support-agent \
+  --labeled-dataset .evalgate/golden/labeled.jsonl \
+  --pull-labels
+
+# Pull the active web prompt into a local file
+evalgate sync \
+  --project-key support-agent \
+  --prompt-id prompt_support \
+  --target-path prompts/support.md \
+  --pull-prompt
+
+# Push an edited local prompt as a new web prompt version
+evalgate sync \
+  --project-key support-agent \
+  --prompt-id prompt_support \
+  --target-path prompts/support.md \
+  --push-prompt
+```
+
 ## Judge Orchestration
 
 The Python SDK supports the same core judge model as the platform:

{evalgate_sdk-3.5.0 → evalgate_sdk-3.5.1}/README.md

@@ -13,7 +13,6 @@ Use it to run assertions, trace agent workflows, inspect platform runs, orchestr
 
 ```bash
 pip install evalgate-sdk
-pip install "evalgate-sdk[cli]"
 ```
 
 Optional extras:
@@ -73,6 +72,35 @@ evalgate judge registry
 evalgate judge presets
 ```
 
+## Web App Sync
+
+The Python CLI uses the same sync contracts as the TypeScript SDK. Local labeled
+JSONL can be pushed into the web app, web-labeled cases can be merged back into
+the same file, and prompt files can round-trip with stale active-version
+protection.
+
+```bash
+# Push local labels into the web app and pull web labels back into JSONL
+evalgate sync \
+  --project-key support-agent \
+  --labeled-dataset .evalgate/golden/labeled.jsonl \
+  --pull-labels
+
+# Pull the active web prompt into a local file
+evalgate sync \
+  --project-key support-agent \
+  --prompt-id prompt_support \
+  --target-path prompts/support.md \
+  --pull-prompt
+
+# Push an edited local prompt as a new web prompt version
+evalgate sync \
+  --project-key support-agent \
+  --prompt-id prompt_support \
+  --target-path prompts/support.md \
+  --push-prompt
+```
+
 ## Judge Orchestration
 
 The Python SDK supports the same core judge model as the platform:

{evalgate_sdk-3.5.0 → evalgate_sdk-3.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "evalgate-sdk"
-version = "3.5.0"
+version = "3.5.1"
 description = "EvalGate Python SDK — CI for AI behavior. Traces, evaluations, assertions, and regression gates for LLM apps."
 readme = "README.md"
 license = "MIT"
@@ -31,6 +31,8 @@ classifiers = [
 dependencies = [
     "httpx>=0.27,<1",
     "pydantic>=2.0,<3",
+    "rich>=13",
+    "typer>=0.12",
 ]
 
 [project.optional-dependencies]
@@ -66,6 +68,8 @@ packages = ["src/evalgate_sdk"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+pythonpath = ["src"]
 
 [tool.ruff]
 target-version = "py310"

evalgate_sdk-3.5.1/src/evalgate_sdk/_version.py

@@ -0,0 +1,3 @@
+__version__ = "3.5.1"
+SDK_VERSION = __version__
+SPEC_VERSION = "3.5.1"

{evalgate_sdk-3.5.0 → evalgate_sdk-3.5.1}/src/evalgate_sdk/cli/__init__.py

@@ -6,10 +6,34 @@ Submodules like config.py, api.py, etc. can be imported without typer.
 
 from __future__ import annotations
 
+import sys
+
 # Lazy initialization - only set up CLI when typer is available
 app = None  # Will be initialized on first access via get_app()
 
 
+def _stream_needs_replacement_errors(stream: object) -> bool:
+    """Return whether the stream encoding cannot represent common CLI glyphs."""
+    encoding = getattr(stream, "encoding", None)
+    if not encoding:
+        return False
+    try:
+        "✓ → ─".encode(encoding)
+        return False
+    except (LookupError, UnicodeEncodeError):
+        return True
+
+
+def _make_output_streams_encoding_safe() -> None:
+    """Prevent Windows legacy code pages from crashing Rich/Typer help output."""
+    for stream in (sys.stdout, sys.stderr):
+        if not _stream_needs_replacement_errors(stream):
+            continue
+        reconfigure = getattr(stream, "reconfigure", None)
+        if reconfigure is not None:
+            reconfigure(errors="replace")
+
+
 def _ensure_typer() -> None:
     """Check that typer is installed, raise helpful error if not."""
     try:
@@ -50,7 +74,9 @@ def get_app():
         print_config,
         run,
         share,
+        sync,
         upgrade,
+        version,
     )
     from evalgate_sdk.cli.judge_commands import judge
     from evalgate_sdk.cli.workflow_commands import controls, integrity, knowledge, plan, trace, workflow
@@ -74,8 +100,10 @@ def get_app():
     app.command("baseline")(baseline)
     app.command("print-config")(print_config)
     app.command("share")(share)
+    app.command("sync")(sync)
     app.command("configure")(configure)
     app.command("upgrade")(upgrade)
+    app.command("version")(version)
     app.command("impact-analysis")(impact_analysis)
     app.command("migrate")(migrate)
 
@@ -116,5 +144,6 @@ def __getattr__(name: str):
 
 def main() -> None:
     """CLI entry point."""
+    _make_output_streams_encoding_safe()
     cli_app = get_app()
     cli_app()