jevper 0.1.0__tar.gz

jevper-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,43 @@
+# Release: tag `vX.Y.Z` -> run the suite, build, publish to PyPI.
+#
+# Publishing uses PyPI trusted publishing (OIDC), so no API token is stored in
+# this repository. One-time setup on PyPI:
+#
+#   pypi.org -> Account -> Publishing -> "Add a pending publisher"
+#     PyPI project name: jevper
+#     Owner:             zhulinchng
+#     Repository name:   jevper
+#     Workflow name:     release.yml
+#     Environment name:  pypi
+#
+# Then: bump `version` in pyproject.toml, commit, and `git push origin vX.Y.Z`.
+# If the project is instead published with an API token, replace the publish
+# step's `password` with `${{ secrets.PYPI_API_TOKEN }}` and drop `id-token`.
+
+name: release
+
+on:
+  push:
+    tags: ["v*"]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+      - run: uv venv --python 3.12
+      - run: uv pip install --python .venv/bin/python -e '.[test]'
+      - run: .venv/bin/python -m pytest -q
+
+  publish:
+    needs: test
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+      - run: uv build
+      - uses: pypa/gh-action-pypi-publish@release/v1

jevper-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+.venv/
+__pycache__/
+*.py[cod]
+.pytest_cache/
+.ruff_cache/
+dist/
+build/
+*.egg-info/

jevper-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 2026 Zhu Lin
+
+   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.

jevper-0.1.0/PKG-INFO

@@ -0,0 +1,240 @@
+Metadata-Version: 2.5
+Name: jevper
+Version: 0.1.0
+Summary: Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
+Project-URL: Homepage, https://github.com/zhulinchng/jevper
+Project-URL: Repository, https://github.com/zhulinchng/jevper
+Project-URL: Issues, https://github.com/zhulinchng/jevper/issues
+Project-URL: Changelog, https://github.com/zhulinchng/jevper/releases
+Author-email: Zhu Lin <zhulin@czl.my>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: classification,confidence,jev,llm,logprobs,openai,structured-output,system-one
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3 :: Only
+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 :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: pydantic>=2.7
+Provides-Extra: test
+Requires-Dist: openai>=1.40; extra == 'test'
+Requires-Dist: pytest>=8; extra == 'test'
+Description-Content-Type: text/markdown
+
+# jevper
+
+`jevper` wraps any OpenAI-like client and gives you a [Jev](https://docs.typesafe.ai) (TypeSafe System One)
+shaped answer instead of prose: you send a `state` plus typed `questions`, and you get back probabilities and
+confidence.
+
+It does not call the hosted TypeSafe API and does not depend on `typesafe-sdk` or `openai` at runtime — the
+client object is duck-typed. Any object exposing `responses.create` or `chat.completions.create` works,
+including a self-hosted llama.cpp server.
+
+```python
+from openai import OpenAI
+from jevper import Choice, SystemOneClient
+
+client = SystemOneClient(OpenAI(), model="gpt-5.6-terra", method="logprobs")
+
+response = client.system_one(
+    state="I was charged twice for the same subscription this month.",
+    questions={
+        "intent": Choice(
+            instructions="Pick the intent of the message.",
+            criteria={
+                "billing": "money, invoices, refunds, charges",
+                "technical": "errors, crashes, login or performance problems",
+                "sales": "pricing, plans, purchasing, upgrades",
+            },
+        )
+    },
+)
+
+answer = response.answers["intent"]
+answer.choice        # "billing"
+answer.probabilities # {"billing": 0.88, "technical": 0.08, "sales": 0.03}
+answer.confidence    # 0.83
+```
+
+## Install
+
+```sh
+pip install jevper
+```
+
+Python 3.10+. The only runtime dependency is `pydantic>=2.7`.
+
+For development:
+
+```sh
+git clone https://github.com/zhulinchng/jevper && cd jevper
+uv venv && uv pip install -e '.[test]'
+pytest -q
+```
+
+## What one call does
+
+```mermaid
+flowchart LR
+    A["state + questions"] --> B["build_messages: system prompt, state turns, few-shot turns, question block"]
+    B --> C{"method"}
+    C -->|logprobs| D["logprobs=true, top_logprobs=20"]
+    C -->|grammar| E["+ GBNF grammar in extra_body"]
+    C -->|structured| F["strict JSON schema: probabilities"]
+    C -->|discrete| G["strict JSON schema: one label"]
+    D --> H["first label token -> softmax over the labels"]
+    E --> H
+    F --> I["probability dict from JSON"]
+    G --> J["one-hot from the chosen label"]
+    H --> K["Answer: choice / noul / score"]
+    I --> K
+    J --> K
+```
+
+Each question becomes its own provider call, so questions are independent and run concurrently
+(`max_concurrency`, default 8). Answers come back keyed by your question ids, in insertion order.
+
+## Questions
+
+Three types, mirroring the Jev API:
+
+| Type | Criteria | Answer |
+| --- | --- | --- |
+| `Noul(instructions=..., criteria={"true": ..., "false": ...})` | optional | `{"type": "noul", "noul": 0.93}` |
+| `Choice(instructions=..., criteria={"billing": "...", ...})` | 2–26 keys | `{"type": "choice", "choice": "billing", "probabilities": {...}, "confidence": 0.83}` |
+| `Score(instructions=..., criteria=["Calm", "Frustrated", "Very angry"])` | 2–10 levels | `{"type": "score", "score": 1.05, "legend": {...}, "probabilities": {...}, "confidence": 0.92}` |
+
+`Score.score` is the probability-weighted level index (`Σ i·pᵢ`, levels zero-based), as in the Jev API.
+`Choice` is capped at 26 options because every method labels options with single letters `A`–`Z`; a larger
+question raises `InvalidQuestionError` telling you to split it.
+
+Questions can also be passed as raw mappings (`{"type": "choice", "criteria": {...}}`) and are validated the
+same way.
+
+## Methods
+
+`method=` decides how the decision is elicited. All four share the same 26-label cap and the same
+label→option mapping, so switching methods does not change your types.
+
+| Method | Request | Readout | Needs |
+| --- | --- | --- | --- |
+| `logprobs` (default) | `logprobs=true, top_logprobs=20` | softmax over the labels' logprobs of the first answer token | a provider that returns chat logprobs (or the Responses surface with `include` logprobs) |
+| `grammar` | the same plus a GBNF `grammar` in `extra_body` | same as `logprobs` | a Chat Completions server that accepts `grammar` (llama.cpp and friends) |
+| `structured` | strict JSON schema, model returns a probability per option | the model's own numbers, rescaled to sum 1 when off by more than `1e-6` | JSON-schema structured output |
+| `discrete` | strict JSON schema, model returns one option | one-hot distribution | JSON-schema structured output |
+
+`logprobs` is the default because it needs no provider-specific field beyond `logprobs`, and it reads the
+model's real distribution rather than a sampled answer. See [docs/methods.md](docs/methods.md) for the exact
+request bodies, readout rules and failure modes.
+
+## Reasoning
+
+Pass `reasoning=ReasoningConfig(...)` to make the model think before it classifies:
+
+```python
+from jevper import ReasoningConfig, reasoning_text
+
+client = SystemOneClient(OpenAI(), model="gpt-5.6-terra", reasoning=ReasoningConfig(effort="medium"))
+
+response = client.system_one(state=..., questions=...)
+reasoning_text(response.reasoning)   # the trace, as text
+```
+
+`mode="auto"` (the default) uses native provider reasoning on the Responses surface and a two-step
+think-then-classify path on Chat Completions, where the analysis text is replayed as an assistant turn before
+the answer. The trace always lands on `response.reasoning`, and the two-step analysis call's usage is counted
+in `response.usage`. See [docs/reasoning.md](docs/reasoning.md).
+
+## Few-shot examples
+
+Examples are chat turns (example state + question block, then the expected answer), so the demonstration is
+always in the format the active method expects. They can be attached at three levels:
+
+```python
+from jevper import Choice, Example, SystemOneClient
+
+question = Choice(
+    criteria={"billing": "...", "technical": "..."},
+    examples=[Example(state="Charged twice for one order", answer="billing")],
+)
+
+client = SystemOneClient(OpenAI(), model="gpt-5.6-terra",
+                         examples=[Example(state="Login fails", answer="technical")])  # fallback for every question
+
+client.system_one(state=..., questions={"intent": question},
+                  examples={"intent": [...]})  # or a bare sequence for all questions
+```
+
+Precedence is question → per call → constructor, and the first non-empty level wins. `examples` is excluded
+from `model_dump()`, so question dumps keep exactly the Jev wire keys. See
+[docs/few-shot.md](docs/few-shot.md).
+
+## Response
+
+```python
+response.model                 # the model actually used
+response.answers               # {"intent": ChoiceAnswer(...)}
+response.nouls / .choices / .scores   # filtered views
+response.usage                 # input_tokens, output_tokens, reasoning_tokens, n_calls, n_retries, latency
+response.reasoning             # tuple[ReasoningContentPart, ...]
+response.debug                 # per-attempt requests/responses, retry reasons, normalization notes
+```
+
+`response.model_dump_json()` serializes to the Jev answer shape — the answer field names and JSON keys match
+`POST /v1/systemone`. Token counts are `None` when any constituent call omitted them; `n_calls` counts every
+provider call including analysis passes and corrective retries, while `n_retries` counts transient-failure
+retries only. See [docs/api.md](docs/api.md) for the full reference.
+
+## Failures
+
+Local problems fail before any request is sent: an invalid question, an empty `questions` mapping, an
+unusable `state`, or `grammar` on a surface that cannot carry a grammar.
+
+| Error | Raised when |
+| --- | --- |
+| `InvalidQuestionError` | question or few-shot example is locally invalid |
+| `UnsupportedMethodError` | `method="grammar"` on the Responses surface |
+| `ClientCapabilityError` | the client lacks the attribute the chosen surface needs, or returned no choices |
+| `LabelReadoutError` | the first answer token is not a label, or no logprobs came back |
+| `MalformedAnswerError` | the JSON answer had an unusable shape after corrective retries |
+| `ProviderError` | a provider call failed; `.attempts` carries the attempt history |
+
+Transient failures (HTTP 429/500/502/503/504/529, or an exception whose class name contains `Connection` or
+`Timeout`) are retried per call with `RetryPolicy(n_retries=2, base_delay=0.5, max_delay=8.0)` and exponential
+backoff `min(base_delay · 3ⁿ, max_delay)`. Unreadable answers get one corrective retry
+(`n_retry_malformed`) with the failure appended to the conversation. `ProviderError` propagates after all
+questions have settled, in question insertion order.
+
+## Verification
+
+```sh
+pytest -q                      # the whole suite runs against a local stub HTTP server; no network, no API keys
+ruff check src tests           # clean except three PYI034 hints (see docs/internals.md)
+```
+
+The suite drives a real `openai` SDK client at a stdlib `ThreadingHTTPServer` stub, so the SDK's own
+serialization path is exercised; see [docs/internals.md](docs/internals.md#testing).
+
+Optional live check, skipped unless both variables are set:
+
+```sh
+LLM_MODEL=gpt-5.6-terra OPENAI_API_KEY=... pytest -q tests/test_live.py
+```
+
+## Docs
+
+- [docs/api.md](docs/api.md) — constructor and `system_one` parameters, answer/usage/debug shapes, errors
+- [docs/methods.md](docs/methods.md) — the four methods, request bodies, readout rules, surface selection
+- [docs/reasoning.md](docs/reasoning.md) — native vs two-step reasoning, traces, encrypted content
+- [docs/few-shot.md](docs/few-shot.md) — example levels, precedence, rendering, structured examples
+- [docs/internals.md](docs/internals.md) — module map, call flow, concurrency, retries, testing
+
+## License
+
+Apache-2.0 — see [LICENSE](LICENSE).