freesolo 0.2.3__tar.gz → 0.2.4__tar.gz

freesolo-0.2.4/.github/workflows/publish-packages.yml

@@ -0,0 +1,96 @@
+name: Publish packages
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "pyproject.toml"
+      - "uv.lock"
+      - "pypi/**"
+      - "examples/**"
+      - ".github/workflows/publish-packages.yml"
+  workflow_dispatch:
+
+concurrency:
+  group: publish-packages-${{ github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  publish-pypi:
+    name: Publish PyPI package
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    env:
+      UV_PUBLISH_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: Read package metadata
+        id: metadata
+        run: |
+          python - <<'PY' >> "$GITHUB_OUTPUT"
+          import tomllib
+
+          with open("pyproject.toml", "rb") as f:
+              project = tomllib.load(f)["project"]
+
+          print(f"name={project['name']}")
+          print(f"version={project['version']}")
+          PY
+
+      - name: Check PyPI for existing version
+        id: pypi
+        env:
+          PACKAGE_NAME: ${{ steps.metadata.outputs.name }}
+          PACKAGE_VERSION: ${{ steps.metadata.outputs.version }}
+        run: |
+          python - <<'PY' >> "$GITHUB_OUTPUT"
+          import os
+          import urllib.error
+          import urllib.request
+
+          name = os.environ["PACKAGE_NAME"]
+          version = os.environ["PACKAGE_VERSION"]
+          url = f"https://pypi.org/pypi/{name}/{version}/json"
+
+          try:
+              with urllib.request.urlopen(url, timeout=30) as response:
+                  exists = response.status == 200
+          except urllib.error.HTTPError as error:
+              if error.code != 404:
+                  raise
+              exists = False
+
+          print(f"exists={'true' if exists else 'false'}")
+          PY
+
+      - name: Skip existing PyPI version
+        if: steps.pypi.outputs.exists == 'true'
+        run: echo "${{ steps.metadata.outputs.name }} ${{ steps.metadata.outputs.version }} is already on PyPI."
+
+      - name: Install uv
+        if: steps.pypi.outputs.exists != 'true'
+        run: python -m pip install --upgrade uv
+
+      - name: Build distributions
+        if: steps.pypi.outputs.exists != 'true'
+        run: |
+          rm -rf dist
+          uv build
+
+      - name: Publish to PyPI
+        if: steps.pypi.outputs.exists != 'true' && env.UV_PUBLISH_TOKEN != ''
+        run: uv publish
+
+      - name: Skip publish without PyPI token
+        if: steps.pypi.outputs.exists != 'true' && env.UV_PUBLISH_TOKEN == ''
+        run: |
+          echo "PYPI_API_TOKEN is not configured; built distributions but skipped upload."
+          echo "Add a PYPI_API_TOKEN repository secret to publish this package."

freesolo-0.2.4/.github/workflows/python-checks.yml

@@ -0,0 +1,41 @@
+name: Python checks
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  checks:
+    name: Ruff and tests
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        run: python3 -m pip install --upgrade uv
+
+      - name: Install dependencies
+        run: uv sync --locked --extra dev
+
+      - name: Python compile check
+        run: python3 -m py_compile $(find pypi tests -name '*.py' -print)
+
+      - name: Ruff check
+        run: uv run --extra dev python -m ruff check .
+
+      - name: Ruff format check
+        run: uv run --extra dev python -m ruff format --check .
+
+      - name: Tests
+        run: uv run --extra dev python -m pytest tests

freesolo-0.2.4/.github/workflows/sync-package-function-usage.yml

@@ -0,0 +1,38 @@
+name: Sync package function usage
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "function_usage_registry.json"
+      - "scripts/sync_package_function_usage.py"
+      - ".github/workflows/sync-package-function-usage.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  sync:
+    name: Sync usage registry
+    runs-on: ubuntu-latest
+    if: ${{ github.ref == 'refs/heads/main' }}
+    env:
+      SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
+      SUPABASE_SERVICE_ROLE_KEY: ${{ secrets.SUPABASE_SERVICE_ROLE_KEY }}
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: Sync package function rows
+        if: env.SUPABASE_URL != '' && env.SUPABASE_SERVICE_ROLE_KEY != ''
+        run: python scripts/sync_package_function_usage.py --remove-stale
+
+      - name: Skip without Supabase secrets
+        if: env.SUPABASE_URL == '' || env.SUPABASE_SERVICE_ROLE_KEY == ''
+        run: echo "SUPABASE_URL and SUPABASE_SERVICE_ROLE_KEY secrets are required to sync usage."

{freesolo-0.2.3 → freesolo-0.2.4}/PKG-INFO

@@ -1,19 +1,25 @@
 Metadata-Version: 2.4
 Name: freesolo
-Version: 0.2.3
+Version: 0.2.4
 Summary: Tracing, evaluation, and training utilities for LLM applications.
-Requires-Python: >=3.10
+Requires-Python: >=3.11
+Requires-Dist: gepa>=0.1.1
 Requires-Dist: httpx>=0.27.0
+Requires-Dist: jsonschema>=4.0.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: opentelemetry-api>=1.28.0
+Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.28.0
+Requires-Dist: opentelemetry-sdk>=1.28.0
+Requires-Dist: pymongo>=4.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: tinker-cookbook>=0.3.0
+Requires-Dist: tinker>=0.19.0
 Requires-Dist: wandb>=0.17.0
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.11.0; extra == 'dev'
 Provides-Extra: examples
-Requires-Dist: anthropic>=0.40.0; extra == 'examples'
-Requires-Dist: google-genai>=1.0.0; extra == 'examples'
 Requires-Dist: openai>=1.0.0; extra == 'examples'
-Provides-Extra: gepa
-Requires-Dist: gepa>=0.1.1; extra == 'gepa'
 Description-Content-Type: text/markdown
 
 # freesolo
@@ -24,36 +30,15 @@ It is built for the lowest-friction integration possible:
 
 1. Install the package
 2. Set `FREESOLO_API_KEY`
-3. Wrap your OpenAI, Anthropic, Gemini, or OpenAI-compatible client
+3. Configure the tracer
 4. Run traces and evaluations from the package APIs
 
-## Current provider support
-
-`freesolo` currently supports automatic client instrumentation for:
-
-- OpenAI
-- Anthropic
-- Gemini
-- OpenAI-compatible clients via `wrap(...)` / `wrap_provider(...)`
-
 ## Install
 
-Install the package plus the provider client you use:
-
-```bash
-pip install freesolo openai
-```
-
-or
-
-```bash
-pip install freesolo anthropic
-```
-
-or
+Install the package:
 
 ```bash
-pip install freesolo google-genai
+pip install freesolo
 ```
 
 ## Environment
@@ -68,107 +53,77 @@ export FREESOLO_API_KEY=fslo_...
 ## Quickstart
 
 ```python
-from openai import OpenAI
-from freesolo import wrap
-
-client = wrap(OpenAI())
-
-result = client.responses.create(
-    model="gpt-4.1-mini",
-    instructions="Reply in plain text.",
-    input=[
-        {
-            "role": "user",
-            "content": [{"type": "input_text", "text": "How do I reset my password?"}],
-        }
-    ],
-)
-
-print(result.output_text or "")
+from freesolo.tracing import configure_tracer, get_tracer
+
+configure_tracer(service_name="my-llm-app")
+tracer = get_tracer()
+
+with tracer.start_as_current_span(
+    "model.call",
+    attributes={
+        "gen_ai.system": "openai",
+        "gen_ai.request.model": "gpt-5.5",
+        "freesolo.input": {"prompt": "How do I reset my password?"},
+    },
+) as span:
+    result = "Reset it from account settings."
+    span.set_attribute("freesolo.output", result)
 ```
 
-## OpenRouter Quickstart
+## Runnable Examples
 
-```python
-from openai import OpenAI
-from freesolo import wrap
+Copy-pasteable examples live in [`examples/`](examples/):
 
-client = wrap(
-    OpenAI(
-        base_url="https://openrouter.ai/api/v1",
-        api_key="YOUR_OPENROUTER_API_KEY",
-    )
-)
+- `tracing_manual_span.py`: configure OpenTelemetry and send one application span.
+- `evaluation_custom_scorer.py`: run custom binary and numeric eval scorers.
+- `evaluation_from_files.py`: run evals from a concrete dataset and environment.
+- `environment.py`: example environment used by evals, training, and GEPA.
+- `support_dataset.py`: example dataset paths and loaders used by evals, SFT, GRPO, and GEPA.
+- `gepa_prompt_example.py`: run the Freesolo GEPA adapter over the example dataset.
+- `training_sft_grpo.py`: start SFT or GRPO training runs from package APIs.
 
-response = client.chat.completions.create(
-    model="openai/gpt-4.1-mini",
-    messages=[
-        {"role": "system", "content": "Reply in plain text."},
-        {"role": "user", "content": "Write a one-sentence launch blurb."},
-    ],
-    max_tokens=120,
-)
-
-print(response.choices[0].message.content or "")
-```
-
-## Gemini Quickstart
-
-```python
-from google import genai
-from freesolo import instrument_gemini
+From a repo checkout:
 
-client = instrument_gemini(genai.Client())
-
-response = client.models.generate_content(
-    model="gemini-2.5-flash",
-    contents="Write a one-sentence release note for traced Gemini support.",
-)
-
-print(response.text or "")
+```bash
+cd freesolo-sdk
+export PYTHONPATH="$PWD/pypi"
+uv run python examples/evaluation_custom_scorer.py --local
 ```
 
-## Group Multiple Model Calls
-
-For agentic or long-horizon tasks, strongly prefer wrapping the whole task in `start_trace(...)` so all of the model calls land in one trace.
-
-For a single one-off OpenAI, Anthropic, or Gemini request, you can skip it.
-
-```python
-from anthropic import Anthropic
-from freesolo import instrument_anthropic, start_trace
-
-client = instrument_anthropic(Anthropic())
-
-with start_trace("support-agent-run"):
-    first = client.messages.create(
-        model="claude-sonnet-4-20250514",
-        max_tokens=64,
-        messages=[{"role": "user", "content": "Say hello"}],
-    )
-    second = client.messages.create(
-        model="claude-sonnet-4-20250514",
-        max_tokens=64,
-        messages=[{"role": "user", "content": "Say goodbye"}],
-    )
-```
+## Public API
+
+The root `freesolo` module intentionally exports no functions. Import from the
+subpackages below; lower-level modules may be importable, but they are
+implementation helpers unless they appear here or in an example.
+
+| Import | Use case |
+| --- | --- |
+| `freesolo.tracing.configure_tracer`, `get_tracer`, `force_flush`, `shutdown` | Send OpenTelemetry traces from an application to Freesolo. |
+| `freesolo.evaluation.EvaluationClient` | Run custom-scorer evals or environment evals and upload results to Freesolo. |
+| `freesolo.evaluation.run_local_evaluation` | Run custom scorers locally without uploading results. |
+| `freesolo.evaluation.CustomScorer`, `BinaryResponse`, `NumericResponse` | Define local scorer logic for eval rows. |
+| `freesolo.evaluation.HostedJudgeClient` and hosted scorer classes | Use hosted LLM-as-judge scorers with OpenRouter-compatible credentials. |
+| `freesolo.datasets.TaskExample`, `Dataset`, `load_dataset` | Load task examples and construct labeled conversations for evals or training. |
+| `freesolo.environments.Environment`, `RewardResult`, `RewardMetric`, `GrpoConfig`, `EnvironmentGeneration` | Define task behavior once for evals, GEPA, SFT, and GRPO. |
+| `freesolo.training.SftConfig`, `TrainGrpoOptions`, `train_sft`, `train_grpo` | Start SFT or GRPO training from package APIs. |
+| `freesolo.gepa.GEPASetup`, `GEPAConfig`, `DefaultReflectionAgent`, `attach_gepa`, `optimize_gepa` | Optimize prompts through the GEPA adapter using the same environment and dataset abstractions. |
+| `freesolo.contracts.load_contract_text`, `extract_contract_spec`, `load_contract_spec`, `build_oracle_messages` | Read contract markdown and build oracle prompt messages. |
+| `freesolo.utils.oracle.generate_ground_truth_records` | Generate ground-truth JSONL records from source examples using a contract, environment, and oracle model. |
+| `freesolo.utils.upload.upload_tinker_checkpoint_to_huggingface` | Upload a Tinker checkpoint to a private Hugging Face model repo. |
 
 ## What Gets Stored
 
-- Trace title if you explicitly pass it to `start_trace("...")`
-- Trace metadata if you explicitly pass it to `start_trace(..., metadata=...)`
-- Input payloads with `system_prompt`, `user_prompt`, and `images`
-- Output payloads as plain text
-- Token usage when available
-- Image inputs with inline previews for the trace UI
+- Native OTLP traces and spans
+- Resource attributes like `service.name`
+- Span names, timings, parent span ids, status, and errors
+- Common model attributes such as `gen_ai.system`, `gen_ai.request.model`, and token counts
+- Optional `freesolo.input` and `freesolo.output` span attributes
 
 ## Notes
 
-- You do not need `@trace()` for ordinary LLM tracing.
-- A single instrumented OpenAI, Anthropic, or Gemini request creates a trace automatically.
-- For OpenAI-compatible providers like OpenRouter, prefer `wrap(...)` instead of provider-specific helpers.
-- For agentic or long-horizon workflows, strongly recommend `start_trace("descriptive-title")` so planning, retries, and follow-up calls stay grouped.
-- Delivery is best-effort by default. Trace ingestion failures do not break your app.
+- Tracing uses native OpenTelemetry protobuf export to `/api/traces/ingest`.
+- Configure third-party OpenTelemetry instrumentors against the provider returned by `configure_tracer(...)`.
+- Delivery is handled by the OpenTelemetry span processor you configure.
 
 ## Evaluations
 
@@ -216,16 +171,15 @@ results = client.run(
 print(results[0].success)
 ```
 
-## Tinker Deployment
+## Tinker Hugging Face Upload
 
-`freesolo.utils.deployment` is a thin proxy for the Modal deployment server. It posts
-a Tinker checkpoint URL to the pinned Modal `/deployments` endpoint and returns
-the server JSON response.
+`freesolo.utils.upload` posts a Tinker checkpoint URL to the Freesolo upload
+service and returns the Hugging Face upload response.
 
 ```python
-from freesolo.utils.deployment import deploy_tinker_checkpoint
+from freesolo.utils.upload import upload_tinker_checkpoint_to_huggingface
 
-result = deploy_tinker_checkpoint(
+result = upload_tinker_checkpoint_to_huggingface(
     "tinker://<run_id>/sampler_weights/final",
     base_model="Qwen/Qwen3.5-35B-A3B",
 )
@@ -235,34 +189,36 @@ print(result["repoId"])
 
 ### Environment-driven evaluations
 
-For training contracts, you can use the same `Environment` adapter for evals,
-SFT, and GRPO. `run_environment` loads examples, builds prompt messages, calls
-your model callback, scores the response through the environment, and uploads
-the same `scorers_data` shape used by the eval DB.
+For training contracts, `Environment` describes task behavior for evals and
+GRPO/RL: prompt construction, response normalization, and reward scoring.
+Dataset loading and labeled conversation construction live in `freesolo.datasets`.
+`run_environment` loads task examples, calls your model callback, scores the
+response through the environment, and uploads the same `scorers_data` shape used
+by the eval DB.
 
 ```python
 from typing import Any
 
 from openai import OpenAI
 
+from freesolo.datasets import TaskExample
 from freesolo.environments import (
     Environment,
     EnvironmentGeneration,
     RewardMetric,
     RewardResult,
-    TaskExample,
 )
 from freesolo.evaluation import EvaluationClient
 
 
-class ContractEnvironment(Environment):
+class PromptEnvironment(Environment):
     def build_prompt_messages(
         self,
         example: TaskExample,
-        contract_text: str,
+        prompt_text: str,
     ):
         return [
-            {"role": "system", "content": contract_text},
+            {"role": "system", "content": prompt_text},
             {"role": "user", "content": example.task},
         ]
 
@@ -359,7 +315,6 @@ from typing import Any
 
 from openai import OpenAI
 
-from freesolo import instrument_openai
 from freesolo.evaluation import CustomScorer, EvaluationClient, NumericResponse
 
 
@@ -403,7 +358,7 @@ class CorrectnessJudge(CustomScorer[NumericResponse]):
         )
 
 
-judge_client = instrument_openai(OpenAI())
+judge_client = OpenAI()
 
 results = EvaluationClient().run(
     name="support-agent-correctness",
@@ -434,11 +389,4 @@ judge = HostedJudgeClient(api_key="YOUR_OPENROUTER_API_KEY")
 scorer = ReferenceCorrectnessScorer(client=judge)
 ```
 
-Tracing is available through namespaced helpers:
-
-```python
-from freesolo.tracing import start_trace
-
-with start_trace("support-agent-run"):
-    ...
-```
+Tracing is available through the OpenTelemetry helpers in `freesolo.tracing`.