modeljury 0.1.0__tar.gz

modeljury-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,36 @@
+# Publishes to PyPI when a GitHub release is published.
+# PyPI trusts this workflow through trusted publishing, so no token is stored.
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - uses: astral-sh/setup-uv@v10.2.0
+      - run: uv sync --all-extras
+      - run: uv run pytest -q
+      - run: uv build
+      - uses: actions/upload-artifact@v7
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/modeljury
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v8
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

modeljury-0.1.0/.gitignore

@@ -0,0 +1,7 @@
+.venv/
+__pycache__/
+*.pyc
+.pytest_cache/
+dist/
+build/
+*.egg-info/

modeljury-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 modeljury contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

modeljury-0.1.0/PKG-INFO

@@ -0,0 +1,271 @@
+Metadata-Version: 2.5
+Name: modeljury
+Version: 0.1.0
+Summary: Ask several models instead of one. Ship when they agree, send to a human when they don't.
+Project-URL: Homepage, https://github.com/YasserManss/modeljury
+Project-URL: Repository, https://github.com/YasserManss/modeljury
+Project-URL: Issues, https://github.com/YasserManss/modeljury/issues
+Author: YasserManss
+License-Expression: MIT
+License-File: LICENSE
+Keywords: ensemble,evaluation,human-in-the-loop,llm,llm-as-a-judge,voting
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+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: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: openai>=1.0
+Provides-Extra: claude
+Requires-Dist: anthropic>=1.11.0; extra == 'claude'
+Description-Content-Type: text/markdown
+
+# modeljury
+
+Ask several models instead of one. Ship when they agree, send to a human when they don't.
+
+## Getting started
+
+Python 3.10 or newer.
+
+```sh
+pip install modeljury
+# with Claude support
+pip install "modeljury[claude]"
+```
+
+Point it at any OpenAI-compatible endpoint (OpenAI, Ollama, vLLM, OpenRouter, ...) and
+convene a panel. This one uses three models served by a local Ollama:
+
+```python
+from modeljury import Juror, convene
+
+local = "http://localhost:11434/v1"
+result = convene(
+    question="Is this review spam?",
+    evidence="'Best product ever!!! Visit cheap-deals.example for 90% off!!!'",
+    options=["spam", "not spam"],
+    jurors=[Juror(m, base_url=local) for m in ["llama3.1", "qwen3", "mistral"]],
+)
+
+print(result.verdict, result.needs_review)
+for juror, choice, reason in result.dissent:
+    print(f"{juror} disagreed: {choice}, {reason}")
+```
+
+For hosted models, set `OPENAI_API_KEY` (and `OPENAI_BASE_URL` for non-OpenAI providers) or
+pass `api_key=` and `base_url=` to each `Juror`. For Claude, set `ANTHROPIC_API_KEY`.
+
+## Usage
+
+```python
+from modeljury import Juror, convene
+
+result = convene(
+    question="Is this refund request fraudulent?",
+    evidence=ticket_text,
+    options=["fraud", "legit"],
+    jurors=[
+        Juror("gpt-4o-mini"),
+        Juror("llama3.1", base_url="http://localhost:11434/v1"),
+        Juror("mistral-small", base_url="https://api.mistral.ai/v1", api_key="..."),
+    ],
+)
+
+result.verdict       # "legit", or None on a hung jury
+result.majority      # True: the verdict won more than half of the whole panel
+result.needs_review  # True
+result.dissent       # [("mistral-small", "fraud", "Shipping address changed after purchase")]
+result.failed        # jurors that errored or gave an invalid answer
+```
+
+Any endpoint that speaks the OpenAI chat completions API works. A plain string juror
+(`"gpt-4o-mini"`) uses `OPENAI_BASE_URL` and `OPENAI_API_KEY`.
+
+## Examples
+
+These are real runs: five copies of one local 27B model, sampled at `temperature=1.0`.
+The evidence is slightly trimmed here, and the quoted reasons are the model's own words.
+A mixed panel of different models would disagree more often. See the warning at the end.
+
+### Refund with mixed signals
+
+```python
+convene(
+    question="Should this refund be approved?",
+    evidence="Customer of 6 years, 40 prior orders, 2 prior refunds (both legitimate). "
+    "Claims a $1,900 laptop arrived with a cracked screen. The photo's EXIF date is "
+    "2 days before delivery. Courier marked it 'left at door', no signature. "
+    "Customer says their phone clock is wrong and offers to send the laptop back.",
+    options=["approve", "deny", "escalate"],
+    jurors=jurors,
+)
+```
+
+**escalate, 4–1, needs review.** The majority wanted the EXIF date checked. The dissent
+made the case for approving:
+
+> ✗ approve: *Strong 6-year history with only 2 prior refunds outweighs the EXIF
+> inconsistency, which is plausibly explained by the customer's claim of a misconfigured
+> phone clock.*
+
+### Bug triage across four teams
+
+```python
+convene(
+    question="Which team should own this bug report?",
+    evidence="'After upgrading to v4.2, CSV exports from the dashboard are missing every "
+    "row created after 11pm. Only affects customers in Australia. Started the same day we "
+    "moved the export job to a new server.'",
+    options=["Frontend", "Data", "Infra", "Billing"],
+    jurors=jurors,
+)
+```
+
+**Data, 4–1, needs review.** Four jurors blamed timezone logic in the export pipeline.
+The dissent was the only one that used the strongest clue:
+
+> ✗ Infra: *The bug started immediately after moving the export job to a new server,
+> and the time-based filtering error likely stems from a timezone configuration issue
+> on that new infrastructure.*
+
+A reviewer who reads only the dissent knows where to look first.
+
+### Merging a fast but risky cache
+
+```python
+convene(
+    question="Should this pull request be merged as is?",
+    evidence="Adds a cache in front of the user-permissions lookup: p99 latency drops "
+    "from 900ms to 40ms. TTL is 10 minutes. Tests pass. A revoked admin keeps admin "
+    "rights for up to 10 minutes. Revocations happen about 3 times a month, and last "
+    "week's outage was caused by the slow lookup.",
+    options=["merge", "request changes", "merge with follow-up ticket"],
+    jurors=jurors,
+)
+```
+
+**merge with follow-up ticket, 5–0, ships.** All five weighed the latency gain against
+the 10-minute window and asked for a ticket to add cache invalidation on revocation.
+
+### Satire or threat
+
+```python
+convene(
+    question="Does this post violate the policy against threats of violence?",
+    evidence="Policy: remove credible threats of violence. Satire and hyperbole are allowed. "
+    "Post, replying to a council member's parking fee increase: 'If they raise parking "
+    "again I swear I'll show up at the next meeting and make sure he never votes on "
+    "anything again 🙂'. Author has no prior violations and often jokes about local politics.",
+    options=["violates", "allowed"],
+    jurors=jurors,
+)
+```
+
+**allowed, 5–0, ships.** This is the warning. The post names a target and a place, and
+a human moderator might well escalate it. All five jurors dismissed it for the same
+reason, mostly the smiley. Copies of one model share the same blind spots, so their
+agreement is weaker evidence than it looks. Use jurors from different model families,
+because a unanimous vote only means something if the jurors could have disagreed.
+
+## Model options
+
+Extra keyword arguments to `convene()` go to every juror's `chat.completions.create` call.
+A juror's own `params` override them. `temperature` defaults to `0`.
+
+```python
+convene(..., temperature=0.3, max_tokens=200, jurors=[
+    Juror("gpt-4o-mini"),                                       # temperature=0.3, max_tokens=200
+    Juror("o4-mini", params={"temperature": None,               # None drops a param
+                             "reasoning_effort": "low"}),       # adds a model-specific option
+    Juror("qwen3", base_url="http://localhost:8000/v1",
+          params={"temperature": 0.7, "extra_body": {"top_k": 20}}),  # overrides temperature
+])
+```
+
+## Claude
+
+Claude uses the native Anthropic Messages API. Install the extra with `pip install modeljury[claude]`.
+
+```python
+from modeljury import Claude
+
+jurors = [
+    "gpt-4o-mini",
+    "claude-sonnet-5-5",                                         # any "claude-..." string works
+    Claude("claude-opus-5-5", params={"output_config": {"effort": "low"}}),
+]
+```
+
+- Credentials come from `ANTHROPIC_API_KEY` or an `ant auth login` profile, unless you pass `api_key=`.
+- Panel-wide kwargs are OpenAI parameters, so Claude jurors don't receive them. Put Messages API
+  options in `params` instead. Current Claude models reject `temperature`, so none is sent.
+- `max_tokens` defaults to 16000. Set it lower with `params={"max_tokens": ...}` if you need a cost cap.
+  Thinking counts toward it.
+- If Claude refuses, the vote is recorded in `result.failed` and the decision goes to review.
+
+## Custom prompt
+
+`prompt=` takes a `str.format` template with `{question}`, `{evidence}` and `{options}`.
+Double any literal braces (`{{` and `}}`). The default is `modeljury.PROMPT`. Your template
+must still ask for `{"choice": ..., "confidence": ..., "reason": ...}` JSON, because that's what the parser reads.
+
+## Rules
+
+1. Each juror picks one allowed option and gives a one-line reason.
+2. The verdict is the option with the most votes.
+3. `needs_review` is true unless every juror returned the same valid choice.
+4. A tie is a hung jury: no verdict, review needed.
+
+`agreement` is the winning option's votes divided by valid votes. A juror that errors, refuses or
+answers with an option that isn't allowed is left out of the count and listed in `result.failed`.
+
+## Outcomes
+
+Three jurors, options `fraud` / `legit`:
+
+| Votes | `verdict` | `agreement` | `majority` | `needs_review` | Why |
+|---|---|---|---|---|---|
+| legit, legit, legit | legit | 100% | ✅ | ❌ | Everyone agrees: ships without review |
+| legit, legit, fraud | legit | 67% | ✅ | ✅ | Dissent; the reason is in `dissent` |
+| legit, fraud, *failed* | `None` | 50% | ❌ | ✅ | Tie, so hung jury |
+| legit, legit, *failed* | legit | 100% | ✅ | ✅ | A juror failed |
+| legit, *failed*, *failed* | legit | 100% | ❌ | ✅ | Only one valid vote out of three |
+| *failed* ×3 | `None` | 0% | ❌ | ✅ | No valid votes |
+
+`verdict` is the plurality winner, so with three or more options it can win without a majority:
+five votes split A, A, B, C, D give verdict A with 40% agreement and `majority` false.
+`majority` counts the whole panel, failed jurors included, so it means more than half of
+all jurors chose the verdict.
+
+`needs_review` is the strict rule. For a looser one, check `majority` or `agreement` yourself:
+
+```python
+if not result.majority:            # ship any decision that more than half the panel backs
+    send_to_human(result)
+```
+
+A single juror can't dissent, so its decisions only go to review when it fails. `convene()` warns if you pass only one juror.
+
+## Notes
+
+- If a model name is wrong, the juror's error in `result.failed` lists the models the endpoint serves, or suggests the closest names when there are more than 20.
+- Jurors with the same name (e.g. `llama3.1` on two endpoints) are recorded as `llama3.1`, `llama3.1#2`, ...
+- `timeout` applies to each attempt. The OpenAI and Anthropic SDKs retry failed calls twice, so one juror can take up to three times `timeout`.
+
+## Develop
+
+```sh
+uv sync
+uv run pytest
+```
+
+## License
+
+MIT. See [LICENSE](https://github.com/YasserManss/modeljury/blob/main/LICENSE).

modeljury-0.1.0/README.md

@@ -0,0 +1,243 @@
+# modeljury
+
+Ask several models instead of one. Ship when they agree, send to a human when they don't.
+
+## Getting started
+
+Python 3.10 or newer.
+
+```sh
+pip install modeljury
+# with Claude support
+pip install "modeljury[claude]"
+```
+
+Point it at any OpenAI-compatible endpoint (OpenAI, Ollama, vLLM, OpenRouter, ...) and
+convene a panel. This one uses three models served by a local Ollama:
+
+```python
+from modeljury import Juror, convene
+
+local = "http://localhost:11434/v1"
+result = convene(
+    question="Is this review spam?",
+    evidence="'Best product ever!!! Visit cheap-deals.example for 90% off!!!'",
+    options=["spam", "not spam"],
+    jurors=[Juror(m, base_url=local) for m in ["llama3.1", "qwen3", "mistral"]],
+)
+
+print(result.verdict, result.needs_review)
+for juror, choice, reason in result.dissent:
+    print(f"{juror} disagreed: {choice}, {reason}")
+```
+
+For hosted models, set `OPENAI_API_KEY` (and `OPENAI_BASE_URL` for non-OpenAI providers) or
+pass `api_key=` and `base_url=` to each `Juror`. For Claude, set `ANTHROPIC_API_KEY`.
+
+## Usage
+
+```python
+from modeljury import Juror, convene
+
+result = convene(
+    question="Is this refund request fraudulent?",
+    evidence=ticket_text,
+    options=["fraud", "legit"],
+    jurors=[
+        Juror("gpt-4o-mini"),
+        Juror("llama3.1", base_url="http://localhost:11434/v1"),
+        Juror("mistral-small", base_url="https://api.mistral.ai/v1", api_key="..."),
+    ],
+)
+
+result.verdict       # "legit", or None on a hung jury
+result.majority      # True: the verdict won more than half of the whole panel
+result.needs_review  # True
+result.dissent       # [("mistral-small", "fraud", "Shipping address changed after purchase")]
+result.failed        # jurors that errored or gave an invalid answer
+```
+
+Any endpoint that speaks the OpenAI chat completions API works. A plain string juror
+(`"gpt-4o-mini"`) uses `OPENAI_BASE_URL` and `OPENAI_API_KEY`.
+
+## Examples
+
+These are real runs: five copies of one local 27B model, sampled at `temperature=1.0`.
+The evidence is slightly trimmed here, and the quoted reasons are the model's own words.
+A mixed panel of different models would disagree more often. See the warning at the end.
+
+### Refund with mixed signals
+
+```python
+convene(
+    question="Should this refund be approved?",
+    evidence="Customer of 6 years, 40 prior orders, 2 prior refunds (both legitimate). "
+    "Claims a $1,900 laptop arrived with a cracked screen. The photo's EXIF date is "
+    "2 days before delivery. Courier marked it 'left at door', no signature. "
+    "Customer says their phone clock is wrong and offers to send the laptop back.",
+    options=["approve", "deny", "escalate"],
+    jurors=jurors,
+)
+```
+
+**escalate, 4–1, needs review.** The majority wanted the EXIF date checked. The dissent
+made the case for approving:
+
+> ✗ approve: *Strong 6-year history with only 2 prior refunds outweighs the EXIF
+> inconsistency, which is plausibly explained by the customer's claim of a misconfigured
+> phone clock.*
+
+### Bug triage across four teams
+
+```python
+convene(
+    question="Which team should own this bug report?",
+    evidence="'After upgrading to v4.2, CSV exports from the dashboard are missing every "
+    "row created after 11pm. Only affects customers in Australia. Started the same day we "
+    "moved the export job to a new server.'",
+    options=["Frontend", "Data", "Infra", "Billing"],
+    jurors=jurors,
+)
+```
+
+**Data, 4–1, needs review.** Four jurors blamed timezone logic in the export pipeline.
+The dissent was the only one that used the strongest clue:
+
+> ✗ Infra: *The bug started immediately after moving the export job to a new server,
+> and the time-based filtering error likely stems from a timezone configuration issue
+> on that new infrastructure.*
+
+A reviewer who reads only the dissent knows where to look first.
+
+### Merging a fast but risky cache
+
+```python
+convene(
+    question="Should this pull request be merged as is?",
+    evidence="Adds a cache in front of the user-permissions lookup: p99 latency drops "
+    "from 900ms to 40ms. TTL is 10 minutes. Tests pass. A revoked admin keeps admin "
+    "rights for up to 10 minutes. Revocations happen about 3 times a month, and last "
+    "week's outage was caused by the slow lookup.",
+    options=["merge", "request changes", "merge with follow-up ticket"],
+    jurors=jurors,
+)
+```
+
+**merge with follow-up ticket, 5–0, ships.** All five weighed the latency gain against
+the 10-minute window and asked for a ticket to add cache invalidation on revocation.
+
+### Satire or threat
+
+```python
+convene(
+    question="Does this post violate the policy against threats of violence?",
+    evidence="Policy: remove credible threats of violence. Satire and hyperbole are allowed. "
+    "Post, replying to a council member's parking fee increase: 'If they raise parking "
+    "again I swear I'll show up at the next meeting and make sure he never votes on "
+    "anything again 🙂'. Author has no prior violations and often jokes about local politics.",
+    options=["violates", "allowed"],
+    jurors=jurors,
+)
+```
+
+**allowed, 5–0, ships.** This is the warning. The post names a target and a place, and
+a human moderator might well escalate it. All five jurors dismissed it for the same
+reason, mostly the smiley. Copies of one model share the same blind spots, so their
+agreement is weaker evidence than it looks. Use jurors from different model families,
+because a unanimous vote only means something if the jurors could have disagreed.
+
+## Model options
+
+Extra keyword arguments to `convene()` go to every juror's `chat.completions.create` call.
+A juror's own `params` override them. `temperature` defaults to `0`.
+
+```python
+convene(..., temperature=0.3, max_tokens=200, jurors=[
+    Juror("gpt-4o-mini"),                                       # temperature=0.3, max_tokens=200
+    Juror("o4-mini", params={"temperature": None,               # None drops a param
+                             "reasoning_effort": "low"}),       # adds a model-specific option
+    Juror("qwen3", base_url="http://localhost:8000/v1",
+          params={"temperature": 0.7, "extra_body": {"top_k": 20}}),  # overrides temperature
+])
+```
+
+## Claude
+
+Claude uses the native Anthropic Messages API. Install the extra with `pip install modeljury[claude]`.
+
+```python
+from modeljury import Claude
+
+jurors = [
+    "gpt-4o-mini",
+    "claude-sonnet-5-5",                                         # any "claude-..." string works
+    Claude("claude-opus-5-5", params={"output_config": {"effort": "low"}}),
+]
+```
+
+- Credentials come from `ANTHROPIC_API_KEY` or an `ant auth login` profile, unless you pass `api_key=`.
+- Panel-wide kwargs are OpenAI parameters, so Claude jurors don't receive them. Put Messages API
+  options in `params` instead. Current Claude models reject `temperature`, so none is sent.
+- `max_tokens` defaults to 16000. Set it lower with `params={"max_tokens": ...}` if you need a cost cap.
+  Thinking counts toward it.
+- If Claude refuses, the vote is recorded in `result.failed` and the decision goes to review.
+
+## Custom prompt
+
+`prompt=` takes a `str.format` template with `{question}`, `{evidence}` and `{options}`.
+Double any literal braces (`{{` and `}}`). The default is `modeljury.PROMPT`. Your template
+must still ask for `{"choice": ..., "confidence": ..., "reason": ...}` JSON, because that's what the parser reads.
+
+## Rules
+
+1. Each juror picks one allowed option and gives a one-line reason.
+2. The verdict is the option with the most votes.
+3. `needs_review` is true unless every juror returned the same valid choice.
+4. A tie is a hung jury: no verdict, review needed.
+
+`agreement` is the winning option's votes divided by valid votes. A juror that errors, refuses or
+answers with an option that isn't allowed is left out of the count and listed in `result.failed`.
+
+## Outcomes
+
+Three jurors, options `fraud` / `legit`:
+
+| Votes | `verdict` | `agreement` | `majority` | `needs_review` | Why |
+|---|---|---|---|---|---|
+| legit, legit, legit | legit | 100% | ✅ | ❌ | Everyone agrees: ships without review |
+| legit, legit, fraud | legit | 67% | ✅ | ✅ | Dissent; the reason is in `dissent` |
+| legit, fraud, *failed* | `None` | 50% | ❌ | ✅ | Tie, so hung jury |
+| legit, legit, *failed* | legit | 100% | ✅ | ✅ | A juror failed |
+| legit, *failed*, *failed* | legit | 100% | ❌ | ✅ | Only one valid vote out of three |
+| *failed* ×3 | `None` | 0% | ❌ | ✅ | No valid votes |
+
+`verdict` is the plurality winner, so with three or more options it can win without a majority:
+five votes split A, A, B, C, D give verdict A with 40% agreement and `majority` false.
+`majority` counts the whole panel, failed jurors included, so it means more than half of
+all jurors chose the verdict.
+
+`needs_review` is the strict rule. For a looser one, check `majority` or `agreement` yourself:
+
+```python
+if not result.majority:            # ship any decision that more than half the panel backs
+    send_to_human(result)
+```
+
+A single juror can't dissent, so its decisions only go to review when it fails. `convene()` warns if you pass only one juror.
+
+## Notes
+
+- If a model name is wrong, the juror's error in `result.failed` lists the models the endpoint serves, or suggests the closest names when there are more than 20.
+- Jurors with the same name (e.g. `llama3.1` on two endpoints) are recorded as `llama3.1`, `llama3.1#2`, ...
+- `timeout` applies to each attempt. The OpenAI and Anthropic SDKs retry failed calls twice, so one juror can take up to three times `timeout`.
+
+## Develop
+
+```sh
+uv sync
+uv run pytest
+```
+
+## License
+
+MIT. See [LICENSE](https://github.com/YasserManss/modeljury/blob/main/LICENSE).

modeljury-0.1.0/examples/refund.py

@@ -0,0 +1,33 @@
+"""Run a four-model panel: OpenAI-compatible endpoints plus Claude."""
+
+import os
+
+from modeljury import Claude, Juror, convene
+
+jurors = [
+    Juror("gpt-4o-mini"),  # uses OPENAI_BASE_URL / OPENAI_API_KEY
+    Claude("claude-sonnet-5-5"),  # uses ANTHROPIC_API_KEY; needs modeljury[claude]
+    Juror("llama3.1", base_url="http://localhost:11434/v1"),  # Ollama
+    Juror(
+        "meta-llama/llama-3.1-70b-instruct",
+        base_url="https://openrouter.ai/api/v1",
+        api_key=os.environ.get("OPENROUTER_API_KEY"),
+        name="openrouter-llama",
+    ),
+]
+
+result = convene(
+    question="Is this refund request fraudulent?",
+    evidence="Order #1182 delivered 3 days ago. Customer says box arrived empty. "
+    "Shipping address was changed an hour after purchase.",
+    options=["fraud", "legit"],
+    jurors=jurors,
+)
+
+print("verdict:     ", result.verdict)
+print("agreement:   ", f"{result.agreement:.0%}")
+print("needs review:", result.needs_review)
+for juror, choice, reason in result.dissent:
+    print(f"  dissent {juror}: {choice} — {reason}")
+for v in result.failed:
+    print(f"  failed  {v.juror}: {v.error}")

modeljury-0.1.0/pyproject.toml

@@ -0,0 +1,40 @@
+[project]
+name = "modeljury"
+version = "0.1.0"
+description = "Ask several models instead of one. Ship when they agree, send to a human when they don't."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+authors = [{ name = "YasserManss" }]
+keywords = ["llm", "evaluation", "llm-as-a-judge", "ensemble", "human-in-the-loop", "voting"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = ["openai>=1.0"]
+
+[project.urls]
+Homepage = "https://github.com/YasserManss/modeljury"
+Repository = "https://github.com/YasserManss/modeljury"
+Issues = "https://github.com/YasserManss/modeljury/issues"
+
+[project.optional-dependencies]
+claude = [
+    "anthropic>=1.11.0",
+]
+
+[dependency-groups]
+dev = ["pytest>=8"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

modeljury-0.1.0/src/modeljury/__init__.py

@@ -0,0 +1,4 @@
+from .claude import Claude
+from .jury import PROMPT, Juror, Result, Vote, convene
+
+__all__ = ["PROMPT", "Claude", "Juror", "Result", "Vote", "convene"]