llmci 0.1.0__tar.gz

llmci-0.1.0/LICENSE

@@ -0,0 +1,189 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work.
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Scaffold AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

llmci-0.1.0/PKG-INFO

@@ -0,0 +1,337 @@
+Metadata-Version: 2.4
+Name: llmci
+Version: 0.1.0
+Summary: CI-native regression testing and migration for LLMs
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/alexminnaar/scaffold
+Project-URL: Documentation, https://github.com/alexminnaar/scaffold#readme
+Project-URL: Repository, https://github.com/alexminnaar/scaffold
+Project-URL: Issues, https://github.com/alexminnaar/scaffold/issues
+Project-URL: Changelog, https://github.com/alexminnaar/scaffold/releases
+Keywords: llm,eval,evaluation,ci,regression,testing,prompt
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click>=8.1
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: litellm>=1.40
+Requires-Dist: rich>=13.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: ruff>=0.4; extra == "dev"
+Requires-Dist: mypy>=1.10; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0; extra == "dev"
+Dynamic: license-file
+
+# Scaffold
+
+CI-native regression testing and migration for LLMs.
+
+Catch quality drops before they merge. Migrate models without breaking things.
+
+Scaffold is not an observability tool — it's a **pre-merge safety gate**. Define eval datasets, set quality thresholds, and let CI block bad changes to your prompts, models, or pipelines.
+
+## Installation
+
+```bash
+pip install llmci
+```
+
+The PyPI package is `llmci`; the CLI command is `scaffold`.
+
+Requires Python 3.11+.
+
+## Quick Start
+
+### 1. Initialize
+
+```bash
+scaffold init
+```
+
+This creates a `scaffold.yaml` config and a starter eval dataset. You'll be asked:
+- **Target mode** — `command` (run any script) or `direct` (call an LLM API)
+- **Task type** — classification, open-ended, or agent
+- **Eval name** — what to call this eval
+
+### 2. Define your eval dataset
+
+Edit the generated `evals/<name>.jsonl`. Each line is a JSON object:
+
+```json
+{"input": "My printer won't connect to wifi", "expected": "hardware"}
+{"input": "I need a refund for order #882", "expected": "billing"}
+```
+
+Or add examples interactively:
+
+```bash
+scaffold dataset add --name my-eval
+```
+
+### 3. Run
+
+```bash
+scaffold run
+```
+
+Output:
+
+```
+## Scaffold Eval Report
+
+| Eval | Metric | Score | Threshold | Status |
+|------|--------|-------|-----------|--------|
+| ticket-classification | accuracy | 0.950 | ≥ 0.9 | ✅ |
+| ticket-classification | f1_macro | 0.940 | ≥ 0.85 | ✅ |
+```
+
+Exit code 0 = all thresholds pass. Exit code 1 = regression detected.
+
+## Configuration
+
+`scaffold.yaml` defines your target, evals, and settings:
+
+```yaml
+version: 1
+
+target:
+  command: "python3 run_prompt.py --input {input_file} --output {output_file}"
+
+evals:
+  - name: ticket-classification
+    dataset: ./evals/tickets.jsonl
+    judge: exact_match
+    metrics:
+      - name: accuracy
+        threshold: 0.90
+        mode: absolute
+      - name: f1_macro
+        threshold: 0.85
+        mode: absolute
+
+settings:
+  parallelism: 5
+  timeout_per_call: 30
+  retries: 1
+```
+
+### Target Modes
+
+**Command mode** — wrap any script, any language:
+
+```yaml
+target:
+  command: "python3 my_pipeline.py --input {input_file} --output {output_file}"
+```
+
+Your script reads a JSON input file and writes a JSON output file with an `"output"` key.
+
+**Direct API mode** — call an LLM provider directly:
+
+```yaml
+target:
+  direct:
+    provider: openai
+    model: gpt-4o-mini
+  prompt_file: prompt.txt
+```
+
+Uses [litellm](https://github.com/BerriAI/litellm) under the hood, so any provider works (OpenAI, Anthropic, Azure, etc.). Set credentials via environment variables.
+
+For internal proxies or custom gateways, add `base_url`:
+
+```yaml
+target:
+  direct:
+    provider: openai
+    model: gpt-4o
+    base_url: https://llm-proxy.internal.company.com/v1
+  prompt_file: prompt.txt
+```
+
+### Judges
+
+| Type | Use case | Config |
+|------|----------|--------|
+| `exact_match` | Classification, deterministic outputs | `judge: exact_match` |
+| `llm` | Open-ended generation, summarization | `judge: {type: llm, model: gpt-4o, rubric: [...]}` |
+| `custom` | Domain-specific logic (JSON validation, etc.) | `judge: {type: custom, module: ./judge.py, function: evaluate}` |
+| `composite` | Agent evaluation with multiple criteria | `judge: {type: composite, criteria: [...]}` |
+
+### Metrics
+
+**Score-based:**
+- `accuracy` — fraction of exact matches (score = 1.0)
+- `pass_rate` — fraction of examples scoring >= 0.5
+- `mean_score` — average judge score
+- `median_score` — median judge score (robust to outliers)
+- `min_score` / `max_score` — worst and best scores in dataset
+- `error_rate` — fraction of examples that errored
+
+**Classification:**
+- `f1_macro`, `f1_micro`, `f1_weighted` — F1 score variants
+- `precision_macro`, `precision_micro`, `precision_weighted` — precision variants
+- `recall_macro`, `recall_micro`, `recall_weighted` — recall variants
+
+**Similarity:**
+- `cosine_similarity` — token-overlap cosine similarity between expected and actual
+
+**Latency:**
+- `latency_mean`, `latency_p50`, `latency_p90`, `latency_p99` — response time percentiles (ms)
+
+Each metric supports two threshold modes:
+- `absolute` — score must be >= threshold (for latency metrics, must be <= threshold)
+- `max_regression` — drop from baseline must be <= threshold (e.g., 0.05 = max 5% drop)
+
+## CI Integration
+
+### GitHub Actions
+
+Add to your workflow:
+
+```yaml
+- uses: alexminnaar/scaffold@main
+  with:
+    compare-to: origin/main
+  env:
+    OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+```
+
+Or use the CLI directly:
+
+```yaml
+- run: pip install llmci
+- run: scaffold run --compare-to=origin/main
+  env:
+    GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+```
+
+When running in GitHub Actions, Scaffold automatically posts eval results as a PR comment.
+
+### Baselines
+
+Store baseline scores on your main branch:
+
+```bash
+scaffold run --update-baseline
+```
+
+Then compare PRs against that baseline:
+
+```bash
+scaffold run --compare-to=main
+```
+
+## Model Migration
+
+When switching models (e.g., GPT-4o to GPT-4.5), Scaffold can automatically tune your prompt to maintain quality parity:
+
+```bash
+scaffold migrate \
+  --from gpt-4o \
+  --to gpt-4.5 \
+  --eval ticket-classification \
+  --optimizer-model gpt-4o
+```
+
+The optimizer:
+1. Splits your dataset into train/validation/holdout
+2. Iteratively suggests minimal prompt modifications
+3. Stops when improvement plateaus (early stopping)
+4. Reports the final holdout score vs. the original model
+
+## Agent Evaluation
+
+Test tool-using and conversational agents with composite judging:
+
+```yaml
+evals:
+  - name: agent-tool-use
+    level: agent
+    dataset: ./evals/scenarios.jsonl
+    judge:
+      type: composite
+      criteria:
+        - name: constraints
+          type: constraint
+          weight: 1.0
+        - name: outcome
+          type: outcome
+          weight: 2.0
+```
+
+Supports:
+- **Single-turn** and **multi-turn** conversations
+- **Constraint checking** — tool call budgets, required/forbidden tools, token limits
+- **Outcome judging** — LLM-based evaluation of final output
+- **Trajectory judging** — LLM-based evaluation of execution path quality
+- **Full replay** or **history injection** modes for multi-turn
+
+## Dataset Tools
+
+```bash
+# Initialize a new dataset
+scaffold dataset init --name my-eval --type classification
+
+# Add examples interactively
+scaffold dataset add --name my-eval
+
+# Analyze coverage and quality
+scaffold dataset check --name my-eval
+
+# Import from CSV or JSON
+scaffold dataset import --name my-eval --from data.csv
+```
+
+## Migrating from Promptfoo
+
+```bash
+scaffold import-promptfoo promptfooconfig.yaml
+```
+
+Converts providers, test assertions, and variables into Scaffold's format.
+
+## Examples
+
+| Example | What it demonstrates |
+|---------|---------------------|
+| [`01-ci-regression`](examples/01-ci-regression/) | Ticket classifier with exact_match + F1 |
+| [`02-model-migration`](examples/02-model-migration/) | Prompt optimization across models |
+| [`03-llm-as-judge`](examples/03-llm-as-judge/) | Open-ended generation with rubric judging |
+| [`04-custom-judge`](examples/04-custom-judge/) | JSON schema validation with a Python judge |
+| [`05-agent-single-turn`](examples/05-agent-single-turn/) | Tool-using agent with constraint checking |
+| [`06-agent-multi-turn`](examples/06-agent-multi-turn/) | Multi-turn conversation testing |
+| [`07-pipeline-level`](examples/07-pipeline-level/) | Full RAG pipeline end-to-end |
+| [`08-fastapi-service`](examples/08-fastapi-service/) | Pre/post processing pipeline with dual-level testing |
+| [`09-summarization-qa`](examples/09-summarization-qa/) | Multi-criteria LLM judge with reference-free evaluation |
+
+## CLI Reference
+
+```
+scaffold run              Run evals and report results
+scaffold migrate          Optimize prompts for a new model
+scaffold init             Generate scaffold.yaml interactively
+scaffold dataset init     Create a new eval dataset
+scaffold dataset add      Add examples interactively
+scaffold dataset check    Analyze dataset coverage
+scaffold dataset import   Import from CSV/JSON
+scaffold import-promptfoo Convert a Promptfoo config
+```
+
+Global flags: `-v` (verbose), `--debug` (full logging), `--version`.
+
+## License
+
+Apache 2.0