Metadata-Version: 2.4
Name: modelgenius-sdk
Version: 0.2.0
Summary: Capture LLM call/response snapshots and validate them against the ModelGenius snapshot format — locally, with no network calls.
Author: ModelGenius
License: 
                                         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
              (an example is provided in the Appendix below).
        
              "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 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 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 those 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
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           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.
        
Project-URL: Homepage, https://github.com/modelgenius/modelgenius-sdk
Project-URL: Documentation, https://github.com/modelgenius/modelgenius-sdk/blob/main/docs/snapshot_format.md
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Quality Assurance
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: jsonschema>=4.18
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: ruff>=0.4; extra == "dev"
Dynamic: license-file

# modelgenius-sdk

[![CI](https://github.com/modelgenius/modelgenius-sdk/actions/workflows/ci.yml/badge.svg)](https://github.com/modelgenius/modelgenius-sdk/actions/workflows/ci.yml)
[![PyPI](https://img.shields.io/pypi/v/modelgenius-sdk.svg)](https://pypi.org/project/modelgenius-sdk/)
[![Python](https://img.shields.io/pypi/pyversions/modelgenius-sdk.svg)](https://pypi.org/project/modelgenius-sdk/)
[![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)

Capture your production LLM calls as local **snapshot** files, and validate
them against the ModelGenius snapshot format — entirely on your machine, with
**zero network calls and zero telemetry**.

[ModelGenius](https://github.com/modelgenius) answers "is it safe to switch
LLM models, and is it worth it?" by replaying your real production requests
against candidate models and comparing quality, cost, and latency. The input
to that analysis is a set of snapshots: your requests, the parameters they
ran with, and (ideally) the responses your current model actually produced.
This SDK is the capture side. It has one runtime dependency (`jsonschema`)
and never imports `openai`, `anthropic`, or `litellm` — it duck-types your
existing client objects.

Three ways to adopt it:

1. **Wrap your client** — one line at startup; every call is spooled to local
   JSONL as it happens, with real outputs, token usage, and latency attached.
2. **Bring your own logs** — if you already log LLM traffic, write it in the
   [snapshot format](docs/snapshot_format.md) and use `modelgenius-sdk
   validate` to check it before uploading.
3. **Bring your OpenTelemetry traces** — if your app is already instrumented
   with the [OTel GenAI semantic conventions](https://github.com/open-telemetry/semantic-conventions-genai)
   (OpenLLMetry, OpenLIT, vendor SDKs, …), convert an OTLP/JSON export with
   `modelgenius-sdk convert otlp` — no app changes needed. Requires message
   content capture to be enabled in your instrumentation (it is off by
   default in OTel; metadata-only spans convert to an actionable error).
   Legacy flattened OpenLLMetry attributes (`gen_ai.prompt.N.*`) are also
   understood. Two gaps are inherent to the conventions and flagged rather
   than guessed: `response_format` JSON schemas and (often) tool definitions
   are not carried in traces — converted records note `enrichment_needed` in
   metadata and the validator reminds you to supply them at upload.

## Install

```bash
pip install modelgenius-sdk
```

## Quickstart

**OpenAI** (sync or async client; streaming supported):

```python
import modelgenius_sdk
from openai import OpenAI

client = modelgenius_sdk.wrap_openai(OpenAI(), workflow_name="support_ticket_triage")
# use `client` exactly as before — every chat.completions call is snapshotted locally
```

**Anthropic** (sync or async client; `messages.create` streaming supported):

```python
import modelgenius_sdk
from anthropic import Anthropic

client = modelgenius_sdk.wrap_anthropic(Anthropic(), workflow_name="math_tutoring")
```

**LiteLLM** (success callback):

```python
import litellm
import modelgenius_sdk

litellm.success_callback.append(modelgenius_sdk.make_litellm_callback(workflow_name="ap_automation"))
```

**Validate** what you captured (or logs you wrote yourself):

```bash
modelgenius-sdk validate ./modelgenius_snapshots
```

The wrapper returns the same client object and never changes call behavior:
your arguments pass through untouched, return values and exceptions propagate
unchanged, and any internal capture error is swallowed (logged once), never
raised into your app.

## What gets captured

One JSON object per call, appended to a local JSONL spool file: the request
(messages, model, temperature, tools, response_format, and the rest of the
request parameters), plus a `captured_output` block with the real response —
output text, tool calls, token usage, latency, and, via the LiteLLM callback,
cost. See [docs/snapshot_format.md](docs/snapshot_format.md) for the full
format, and [examples/](examples/) for validated sample files.

The more you capture, the more the analysis can do:

| You provide | You unlock |
| --- | --- |
| `captured_output` | Baseline scored from real production outputs — no baseline replay, real latency/cost preserved |
| `usage` + `cost_usd` | Honest savings baseline from actual spend |
| `workflow_name` + `call_name` (or `workflow_id`) | Precise workflow grouping instead of content-based inference |
| `tools` / `response_format` | Deterministic output-contract checks on every candidate |
| `model` | Automatic baseline identification |

Full table with grouping precedence: [docs/snapshot_format.md](docs/snapshot_format.md#what-each-optional-field-unlocks).

## Configuration

Everything can be set in code via `CaptureConfig`, or via environment
variables:

```python
from modelgenius_sdk import CaptureConfig, wrap_openai

config = CaptureConfig(
    spool_dir="/var/log/myapp/snapshots",
    workflow_name="support_ticket_triage",
    call_name="classify_ticket",
    sample_rate=0.25,          # capture 25% of calls
)
client = wrap_openai(OpenAI(), config)
```

| Environment variable | Effect | Default |
| --- | --- | --- |
| `MODELGENIUS_CAPTURE` | Set to `0`, `false`, or `no` (case-insensitive) to disable capture entirely — the kill switch | enabled |
| `MODELGENIUS_CAPTURE_DIR` | Spool directory for snapshot files | `./modelgenius_snapshots` |
| `MODELGENIUS_CAPTURE_SAMPLE_RATE` | Fraction of calls to capture, `0.0`–`1.0` | `1.0` |
| `MODELGENIUS_CAPTURE_DEBUG` | Set to `1` to make internal capture errors raise instead of being swallowed (for tests/debugging) | off |

Explicit `CaptureConfig` values win over environment variables. The sampling
decision is made once per call, before dispatch, so a streamed response is
either fully captured or not at all.

### Redaction and filtering

You stay in control of what lands on disk:

```python
def redact(record: dict):
    # Called with the full record just before it is written.
    for message in record.get("messages", []):
        if isinstance(message.get("content"), str):
            message["content"] = scrub_pii(message["content"])
    if record.get("metadata", {}).get("tenant_tier") == "enterprise":
        return None  # returning None drops the record entirely
    return record

def only_prod_traffic(request_kwargs: dict) -> bool:
    # Called with the request kwargs before capture is attempted.
    return request_kwargs.get("user") != "internal-smoke-test"

config = CaptureConfig(
    workflow_name="support_ticket_triage",
    redact=redact,
    request_filter=only_prod_traffic,
    sample_rate=0.1,
)
```

### Spool files and rotation

Records are appended to
`<spool_dir>/snapshots-<YYYYMMDD>-<pid>-<seq>.jsonl` — one JSON object per
line, flushed after every write, safe across processes (each PID writes its
own file). When the current file exceeds `max_file_bytes` (default 64 MiB)
the writer rotates to the next sequence number. The spool directory is
created lazily on first write. Point `modelgenius-sdk validate` (or the
ModelGenius upload step) at the directory when you are ready.

## Trust posture

- **Local-only.** The library makes no network calls of its own — the only
  network traffic is your unmodified provider call. Uploading snapshots to
  ModelGenius is a separate, deliberate step you take elsewhere.
- **No telemetry.** Nothing is phoned home. Ever.
- **Fail-open.** Capture errors never raise into your application and never
  alter the provider call, its return value, or its exceptions.
- **You control the data.** Redaction hook, request filter, sampling, and a
  one-variable kill switch (`MODELGENIUS_CAPTURE=0`).
- **Small and auditable.** A handful of modules, one dependency, no provider
  SDK imports — read the whole thing in one sitting.

## CLI

```bash
modelgenius-sdk validate PATH [--json] [--strict] [--quiet]
modelgenius-sdk convert otlp PATH [-o OUTPUT.jsonl] [--json] [--quiet]
modelgenius-sdk version
```

`validate` accepts a `.jsonl` file, a `.json` file (object or array), or a
directory of both. Exit code 0 means every record is accepted by the same
semantics as the ModelGenius upload path; warnings point out optional fields
that would unlock capability. `--strict` turns warnings into failures (useful
in CI — this repo validates its own `examples/` on every push).

`convert otlp` converts an OTLP/JSON trace export (a `.json` payload or a
collector file-exporter `.jsonl`) into snapshot JSONL and validates the
result in one step. Exit code 0 means every GenAI span converted and
validated; per-span problems (e.g. content capture disabled in your
instrumentation) are reported individually and exit 1.

## Limitations (v0)

- Failed provider calls are not captured (only successful responses).
- OpenAI: `chat.completions` only; the `responses` API surface is not wrapped yet.
- Anthropic: `messages.create` (including `stream=True`) is captured; the
  `messages.stream()` helper is not yet.
- LiteLLM: the callback is sync-only (litellm accepts sync callbacks for
  async paths).

## Roadmap

- Direct upload client (`modelgenius-sdk push`) as an explicit, opt-in step
- Continuous monitoring mode (rolling capture windows + scheduled re-evaluation)
- TypeScript SDK
- OpenAI `responses` surface and Anthropic `messages.stream()` capture

## License

[Apache-2.0](LICENSE).
