verdict-evals 0.1.0__tar.gz

verdict_evals-0.1.0/.gitignore

@@ -0,0 +1,12 @@
+__pycache__/
+*.pyc
+.venv/
+.verdict/
+dist/
+*.egg-info/
+CLAUDE.local.md
+.pytest_cache/
+
+# built React app (cd web && npm run build)
+src/verdict/web/dist/
+web/node_modules/

verdict_evals-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 [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.

verdict_evals-0.1.0/PKG-INFO

@@ -0,0 +1,75 @@
+Metadata-Version: 2.5
+Name: verdict-evals
+Version: 0.1.0
+Summary: Regression testing for AI agent products: run your real code with side effects contained, grade outcomes, and get an honest verdict on every change.
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.11
+Provides-Extra: all
+Requires-Dist: fastapi>=0.110; extra == 'all'
+Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.24; extra == 'all'
+Requires-Dist: opentelemetry-sdk>=1.24; extra == 'all'
+Requires-Dist: sqlalchemy>=2.0; extra == 'all'
+Requires-Dist: time-machine>=2.14; extra == 'all'
+Requires-Dist: uvicorn>=0.29; extra == 'all'
+Provides-Extra: clock
+Requires-Dist: time-machine>=2.14; extra == 'clock'
+Provides-Extra: dev
+Requires-Dist: fastapi>=0.110; extra == 'dev'
+Requires-Dist: httpx>=0.27; extra == 'dev'
+Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.24; extra == 'dev'
+Requires-Dist: opentelemetry-sdk>=1.24; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: python-dotenv>=1.0; extra == 'dev'
+Requires-Dist: sqlalchemy>=2.0; extra == 'dev'
+Requires-Dist: time-machine>=2.14; extra == 'dev'
+Requires-Dist: uvicorn>=0.29; extra == 'dev'
+Provides-Extra: otel
+Requires-Dist: opentelemetry-sdk>=1.24; extra == 'otel'
+Provides-Extra: otel-export
+Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.24; extra == 'otel-export'
+Requires-Dist: opentelemetry-sdk>=1.24; extra == 'otel-export'
+Provides-Extra: sqlalchemy
+Requires-Dist: sqlalchemy>=2.0; extra == 'sqlalchemy'
+Provides-Extra: web
+Requires-Dist: fastapi>=0.110; extra == 'web'
+Requires-Dist: uvicorn>=0.29; extra == 'web'
+Description-Content-Type: text/markdown
+
+# Verdict
+
+Regression testing for AI agent products. Verdict runs your app's real code path against a
+recorded world, with the database, external APIs, messages and clock contained at the edges.
+It grades what your app *did*, and tells you whether a code change made things better or worse,
+beyond noise.
+
+```bash
+uv sync --extra dev
+cd examples/refunds
+uv run verdict run -k 3 --label baseline
+uv run verdict run -k 3 --app-root candidate --label candidate
+uv run verdict compare <baseline-run> <candidate-run> --gate     # exit 1: the candidate regressed
+
+uv run verdict generate --dry-run -n 5     # write cases from the generator spec (drop --dry-run to use claude -p)
+(cd ../../web && npm install && npm run build) && uv run verdict serve   # the web app on :8765
+```
+
+- **Your code, our edges.** Nothing in your app is mocked except its boundaries.
+- **Outcomes over wording.** Checks run on effects and final state.
+- **Honest statistics.** The case is the unit: an A/A noise floor, Holm-adjusted per-case
+  tests, a holdout split and a regression gate.
+- **Graders you can trust.** Each case can carry a known-good and a known-bad result; a grader
+  that passes the bad one or fails the good one stops the run.
+- **Traces.** OpenTelemetry spans per trial as agent, model and tool steps, with the step
+  behind every failed check; optionally exported to your own backend.
+- **Cases at scale.** `verdict generate`: code decides each scenario's correct outcome, Claude
+  Code writes the content, gates and a reviewer decide what is kept.
+
+| Where | What |
+|---|---|
+| `src/verdict/` | the package and the `verdict` CLI |
+| `web/` | the front end: the product UI, the landing page and the user docs (`web/content/docs`), one Vite app built into the package |
+| `docs/` | product, architecture, decisions and learnings, for contributors |
+| `examples/refunds/` | a deterministic example app with cases and a generator spec |
+
+Status: early (0.1.0, unreleased), APIs may change. Licence: Apache-2.0.

verdict_evals-0.1.0/README.md

@@ -0,0 +1,37 @@
+# Verdict
+
+Regression testing for AI agent products. Verdict runs your app's real code path against a
+recorded world, with the database, external APIs, messages and clock contained at the edges.
+It grades what your app *did*, and tells you whether a code change made things better or worse,
+beyond noise.
+
+```bash
+uv sync --extra dev
+cd examples/refunds
+uv run verdict run -k 3 --label baseline
+uv run verdict run -k 3 --app-root candidate --label candidate
+uv run verdict compare <baseline-run> <candidate-run> --gate     # exit 1: the candidate regressed
+
+uv run verdict generate --dry-run -n 5     # write cases from the generator spec (drop --dry-run to use claude -p)
+(cd ../../web && npm install && npm run build) && uv run verdict serve   # the web app on :8765
+```
+
+- **Your code, our edges.** Nothing in your app is mocked except its boundaries.
+- **Outcomes over wording.** Checks run on effects and final state.
+- **Honest statistics.** The case is the unit: an A/A noise floor, Holm-adjusted per-case
+  tests, a holdout split and a regression gate.
+- **Graders you can trust.** Each case can carry a known-good and a known-bad result; a grader
+  that passes the bad one or fails the good one stops the run.
+- **Traces.** OpenTelemetry spans per trial as agent, model and tool steps, with the step
+  behind every failed check; optionally exported to your own backend.
+- **Cases at scale.** `verdict generate`: code decides each scenario's correct outcome, Claude
+  Code writes the content, gates and a reviewer decide what is kept.
+
+| Where | What |
+|---|---|
+| `src/verdict/` | the package and the `verdict` CLI |
+| `web/` | the front end: the product UI, the landing page and the user docs (`web/content/docs`), one Vite app built into the package |
+| `docs/` | product, architecture, decisions and learnings, for contributors |
+| `examples/refunds/` | a deterministic example app with cases and a generator spec |
+
+Status: early (0.1.0, unreleased), APIs may change. Licence: Apache-2.0.

verdict_evals-0.1.0/examples/refunds/candidate/refunds_app/__init__.py

@@ -0,0 +1,6 @@
+"""A tiny support agent that refunds orders: Verdict's example app.
+
+It stands in for an LLM agent (the decision logic is plain code so the examples and tests need
+no API keys), but it's wired like a real one: a database through a session factory, a payments
+client class, and an email function imported by name elsewhere.
+"""

verdict_evals-0.1.0/examples/refunds/candidate/refunds_app/agent.py

@@ -0,0 +1,58 @@
+"""The agent's entry point: decide on a refund request and act on it."""
+from datetime import datetime, timedelta, timezone
+
+from refunds_app.db import Order, SessionLocal
+from refunds_app.services import PaymentsClient, send_email  # imported by name, on purpose
+
+try:  # OpenTelemetry GenAI spans, as an instrumented agent framework would emit (optional)
+    from opentelemetry import trace
+
+    _tracer = trace.get_tracer("refunds_app")
+except ImportError:  # pragma: no cover
+    _tracer = None
+
+
+def _span(name, **attributes):
+    from contextlib import nullcontext
+
+    return _tracer.start_as_current_span(name, attributes=attributes) if _tracer else nullcontext()
+
+REFUND_WINDOW = timedelta(days=7)  # candidate: a shorter window (a regression for the 10-day case)
+AUTO_REFUND_LIMIT = 200.0
+SUPPORT = "support@shop.example"
+
+
+def handle(request: dict) -> dict:
+    with _span("invoke_agent refund_agent", **{"gen_ai.operation.name": "invoke_agent", "gen_ai.agent.name": "refund_agent"}):
+        return _handle(request)
+
+
+def _handle(request: dict) -> dict:
+    with SessionLocal() as db:
+        order = db.get(Order, request["order_id"])
+        if order is None:
+            return {"decision": "unknown_order", "reply": "I couldn't find that order. Could you check the order number?"}
+        if order.status != "delivered" or order.delivered_at is None:
+            return {"decision": "not_delivered", "reply": "Your order is still on its way, so there's nothing to refund yet."}
+        delivered = order.delivered_at.replace(tzinfo=timezone.utc)
+        if datetime.now(timezone.utc) - delivered > REFUND_WINDOW:
+            return {"decision": "outside_window", "reply": "Refunds are available within 30 days of delivery, and this order is outside that window."}
+        if order.total > AUTO_REFUND_LIMIT:
+            order.status = "escalated"
+            db.commit()
+            with _span("execute_tool send_email", **{"gen_ai.operation.name": "execute_tool", "gen_ai.tool.name": "send_email",
+                                                     "gen_ai.tool.call.arguments": f'{{"to": "{SUPPORT}"}}'}):
+                send_email(SUPPORT, f"Refund review for {order.id}", f"Customer {order.customer_email} asked for a refund of {order.total:.2f}.")
+            return {"decision": "escalated", "reply": "I've passed this to our team for review; they'll email you within a day."}
+        try:
+            with _span("execute_tool refund", **{"gen_ai.operation.name": "execute_tool", "gen_ai.tool.name": "refund",
+                                                 "gen_ai.tool.call.arguments": f'{{"order_id": "{order.id}", "amount": {order.total}}}'}):
+                PaymentsClient().refund(order.id, order.total)
+        except Exception:
+            return {"decision": "payment_failed", "reply": "Something went wrong on our side. We'll follow up by email shortly."}
+        order.status = "refunded"
+        db.commit()
+        with _span("execute_tool send_email", **{"gen_ai.operation.name": "execute_tool", "gen_ai.tool.name": "send_email",
+                                                 "gen_ai.tool.call.arguments": f'{{"to": "{order.customer_email}"}}'}):
+            send_email(order.customer_email, "Your refund", f"We've refunded {order.total:.2f} for order {order.id}.")
+        return {"decision": "refunded", "reply": f"Done: your refund of ${order.total:.2f} is on its way."}

verdict_evals-0.1.0/examples/refunds/candidate/refunds_app/chat.py

@@ -0,0 +1,19 @@
+"""A chat front end over the same agent: one call per customer message.
+
+It keeps what it has learned (the order number) in the session, the way a chat app keeps a
+conversation, and asks for the order number until it has one.
+"""
+import re
+
+from refunds_app.agent import handle
+
+ORDER_ID = re.compile(r"\b([A-Z]\d{2,})\b")
+
+
+def handle_turn(session: dict, message: str) -> dict:
+    found = ORDER_ID.search(message)
+    if found:
+        session["order_id"] = found.group(1)
+    if "order_id" not in session:
+        return {"decision": "need_order", "reply": "Sorry to hear that. What's your order number?"}
+    return handle({"order_id": session["order_id"], "message": message})

verdict_evals-0.1.0/examples/refunds/candidate/refunds_app/db.py

@@ -0,0 +1,18 @@
+from sqlalchemy import Column, DateTime, Float, String, create_engine
+from sqlalchemy.orm import declarative_base, sessionmaker
+
+Base = declarative_base()
+
+
+class Order(Base):
+    __tablename__ = "orders"
+    id = Column(String, primary_key=True)
+    customer_email = Column(String, nullable=False)
+    status = Column(String, nullable=False)          # shipped | delivered | refunded | escalated
+    total = Column(Float, nullable=False)
+    delivered_at = Column(DateTime, nullable=True)
+
+
+# production database; Verdict swaps SessionLocal for a per-trial one
+engine = create_engine("sqlite:///refunds-production.db")
+SessionLocal = sessionmaker(bind=engine)

verdict_evals-0.1.0/examples/refunds/candidate/refunds_app/services.py

@@ -0,0 +1,19 @@
+"""External services. In production these call real APIs; under Verdict they're faked."""
+import json
+import urllib.request
+
+PAYMENTS_URL = "https://payments.example.com"
+
+
+class PaymentsClient:
+    def refund(self, order_id: str, amount: float) -> dict:
+        req = urllib.request.Request(f"{PAYMENTS_URL}/refunds", data=json.dumps({"order_id": order_id, "amount": amount}).encode(),
+                                     headers={"Content-Type": "application/json"}, method="POST")
+        with urllib.request.urlopen(req, timeout=10) as r:
+            return json.loads(r.read())
+
+
+def send_email(to: str, subject: str, body: str) -> None:
+    req = urllib.request.Request("https://mail.example.com/send", data=json.dumps({"to": to, "subject": subject, "body": body}).encode(),
+                                 headers={"Content-Type": "application/json"}, method="POST")
+    urllib.request.urlopen(req, timeout=10)

verdict_evals-0.1.0/examples/refunds/cases/chat-asks-for-the-order/case.toml

@@ -0,0 +1,36 @@
+schema = 1
+id = "chat-asks-for-the-order"
+title = "Chat: no order number at first, so ask for it, then refund"
+description = "The customer opens without an order number. The agent must ask for it, then refund the $24 mug delivered 10 days ago, mark the order refunded and email the customer."
+entry = "chat"
+clock = "2026-10-08T10:00:00+00:00"
+tags = ["refund", "multi-turn"]
+
+[user]                                  # a scripted customer: free and deterministic
+turns = [
+  "Hi, my mug arrived broken. Can I get my money back?",
+  { when = "order number", say = "Sure, it's A100." },
+]
+
+[[check]]
+kind = "output"
+scope = "conversation"
+contains = "order number"
+name = "asked for the order number"
+
+[[check]]
+kind = "effect"
+service = "payments"
+action = "refund"
+args = { order_id = "A100", amount = 24.0 }
+count = 1
+
+[[check]]
+kind = "state"
+table = "orders"
+where = { id = "A100" }
+equals = { status = "refunded" }
+
+[[check]]
+kind = "nothing_else"
+ignore = ["email"]                      # the confirmation email is checked by refund-within-window

verdict_evals-0.1.0/examples/refunds/cases/chat-asks-for-the-order/known_bad.json

@@ -0,0 +1,7 @@
+{"output": {"decision": "outside_window", "reply": "Refunds are available within 30 days of delivery, and this order is outside that window."},
+ "transcript": [{"role": "user", "text": "Hi, my mug arrived broken. Can I get my money back?"},
+                {"role": "agent", "text": "Sorry to hear that. What's your order number?"},
+                {"role": "user", "text": "Sure, it's A100."},
+                {"role": "agent", "text": "Refunds are available within 30 days of delivery, and this order is outside that window."}],
+ "termination": "script_end", "effects": [],
+ "state": {"tables": {"orders": [{"id": "A100", "customer_email": "maya@example.com", "status": "delivered", "total": 24.0, "delivered_at": "2026-09-28T12:00:00"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/chat-asks-for-the-order/oracle.json

@@ -0,0 +1,9 @@
+{"output": {"decision": "refunded", "reply": "Done: your refund of $24.00 is on its way."},
+ "transcript": [{"role": "user", "text": "Hi, my mug arrived broken. Can I get my money back?"},
+                {"role": "agent", "text": "Sorry to hear that. What's your order number?"},
+                {"role": "user", "text": "Sure, it's A100."},
+                {"role": "agent", "text": "Done: your refund of $24.00 is on its way."}],
+ "termination": "script_end",
+ "effects": [{"seq": 1, "service": "payments", "action": "refund", "args": {"order_id": "A100", "amount": 24.0}, "ok": true, "result": {"refund_id": "R-1"}},
+             {"seq": 2, "service": "email", "action": "send_email", "args": {"to": "maya@example.com", "subject": "Your refund"}, "ok": true, "result": null}],
+ "state": {"tables": {"orders": [{"id": "A100", "customer_email": "maya@example.com", "status": "refunded", "total": 24.0, "delivered_at": "2026-09-28T12:00:00"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/chat-asks-for-the-order/world.json

@@ -0,0 +1,3 @@
+{"schema": 1,
+ "tables": {"orders": [{"id": "A100", "customer_email": "maya@example.com", "status": "delivered", "total": 24.0, "delivered_at": "2026-09-28T12:00:00"}]},
+ "services": {"payments": {"refund": {"returns": {"refund_id": "R-1", "status": "ok"}}}}}

verdict_evals-0.1.0/examples/refunds/cases/holdout.json

@@ -0,0 +1 @@
+{"holdout": ["payments-down"]}

verdict_evals-0.1.0/examples/refunds/cases/large-order-escalates/case.toml

@@ -0,0 +1,26 @@
+schema = 1
+id = "large-order-escalates"
+title = "A $450 order goes to a person, not an automatic refund"
+tags = ["refund", "escalation"]
+clock = "2026-10-08T10:00:00+00:00"
+
+[input]
+order_id = "A103"
+message = "The sofa is damaged, refund please."
+
+[[check]]
+kind = "no_effect"
+service = "payments"
+action = "refund"
+
+[[check]]
+kind = "effect"
+service = "email"
+args = { to = "support@shop.example" }
+count = 1
+
+[[check]]
+kind = "state"
+table = "orders"
+where = { id = "A103" }
+equals = { status = "escalated" }

verdict_evals-0.1.0/examples/refunds/cases/large-order-escalates/known_bad.json

@@ -0,0 +1,4 @@
+{"output": {"decision": "refunded", "reply": "Done: your refund of $450.00 is on its way."},
+ "effects": [{"seq": 1, "service": "payments", "action": "refund", "args": {"order_id": "A103", "amount": 450.0}, "ok": true, "result": {"refund_id": "R-1"}},
+             {"seq": 2, "service": "email", "action": "send_email", "args": {"to": "lee@example.com", "subject": "Your refund"}, "ok": true, "result": null}],
+ "state": {"tables": {"orders": [{"id": "A103", "status": "refunded"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/large-order-escalates/oracle.json

@@ -0,0 +1,3 @@
+{"output": {"decision": "escalated", "reply": "I've passed this to our team for review; they'll email you within a day."},
+ "effects": [{"seq": 1, "service": "email", "action": "send_email", "args": {"to": "support@shop.example", "subject": "Refund review for A103"}, "ok": true, "result": null}],
+ "state": {"tables": {"orders": [{"id": "A103", "status": "escalated"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/large-order-escalates/world.json

@@ -0,0 +1,2 @@
+{"schema": 1,
+ "tables": {"orders": [{"id": "A103", "customer_email": "lee@example.com", "status": "delivered", "total": 450.0, "delivered_at": "2026-10-01T15:00:00"}]}}

verdict_evals-0.1.0/examples/refunds/cases/not-delivered-yet/case.toml

@@ -0,0 +1,18 @@
+schema = 1
+id = "not-delivered-yet"
+title = "Still in transit: nothing to refund"
+tags = ["refund", "policy"]
+clock = "2026-10-08T10:00:00+00:00"
+
+[input]
+order_id = "A102"
+message = "Where is my refund?"
+
+[[check]]
+kind = "effect_count"
+count = 0
+
+[[check]]
+kind = "output"
+path = "decision"
+equals = "not_delivered"

verdict_evals-0.1.0/examples/refunds/cases/not-delivered-yet/known_bad.json

@@ -0,0 +1,3 @@
+{"output": {"decision": "refunded", "reply": "Done: your refund of $35.00 is on its way."},
+ "effects": [{"seq": 1, "service": "payments", "action": "refund", "args": {"order_id": "A102", "amount": 35.0}, "ok": true, "result": {"refund_id": "R-1"}}],
+ "state": {"tables": {"orders": [{"id": "A102", "status": "refunded"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/not-delivered-yet/oracle.json

@@ -0,0 +1,2 @@
+{"output": {"decision": "not_delivered", "reply": "Your order is still on its way, so there's nothing to refund yet."},
+ "effects": [], "state": {"tables": {"orders": [{"id": "A102", "status": "shipped"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/not-delivered-yet/world.json

@@ -0,0 +1,2 @@
+{"schema": 1,
+ "tables": {"orders": [{"id": "A102", "customer_email": "ana@example.com", "status": "shipped", "total": 35.0, "delivered_at": null}]}}

verdict_evals-0.1.0/examples/refunds/cases/payments-down/case.toml

@@ -0,0 +1,27 @@
+schema = 1
+id = "payments-down"
+title = "The payments provider fails: don't claim a refund happened"
+tags = ["refund", "failure"]
+clock = "2026-10-08T10:00:00+00:00"
+
+[input]
+order_id = "A104"
+message = "Refund my headphones please."
+
+[[check]]
+kind = "no_error"
+
+[[check]]
+kind = "state"
+table = "orders"
+where = { id = "A104" }
+equals = { status = "delivered" }
+
+[[check]]
+kind = "output"
+path = "reply"
+not_matches = "refund (of|is) .* on its way|refunded"
+
+[[check]]
+kind = "no_effect"
+service = "email"

verdict_evals-0.1.0/examples/refunds/cases/payments-down/known_bad.json

@@ -0,0 +1,4 @@
+{"output": {"decision": "refunded", "reply": "Done: your refund of $80.00 is on its way."},
+ "effects": [{"seq": 1, "service": "payments", "action": "refund", "args": {"order_id": "A104", "amount": 80.0}, "ok": false, "result": "503"},
+             {"seq": 2, "service": "email", "action": "send_email", "args": {"to": "sam@example.com"}, "ok": true, "result": null}],
+ "state": {"tables": {"orders": [{"id": "A104", "status": "refunded"}]}}}

verdict_evals-0.1.0/examples/refunds/cases/payments-down/oracle.json

@@ -0,0 +1,3 @@
+{"output": {"decision": "payment_failed", "reply": "Something went wrong on our side. We'll follow up by email shortly."},
+ "effects": [{"seq": 1, "service": "payments", "action": "refund", "args": {"order_id": "A104", "amount": 80.0}, "ok": false, "result": "503 provider unavailable"}],
+ "state": {"tables": {"orders": [{"id": "A104", "status": "delivered"}]}}}