ciagent 0.2.0__tar.gz

ciagent-0.2.0/.gitignore

@@ -0,0 +1,24 @@
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+venv/
+.venv/
+env/
+.env
+
+# Distribution
+dist/
+build/
+*.egg-info/
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+.DS_Store
+
+# Agent CI
+golden/
+test_results/

ciagent-0.2.0/CHANGELOG.md

@@ -0,0 +1,11 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+### Added
+- Initial project structure and setup.

ciagent-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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.

ciagent-0.2.0/PKG-INFO

@@ -0,0 +1,322 @@
+Metadata-Version: 2.4
+Name: ciagent
+Version: 0.2.0
+Summary: Continuous Integration for AI Agents. Catch cost spikes and logic regressions before production.
+Project-URL: Documentation, https://github.com/agentci-org/agentci#readme
+Project-URL: Repository, https://github.com/agentci-org/agentci.git
+Project-URL: Issues, https://github.com/agentci-org/agentci/issues
+License: Apache-2.0
+License-File: LICENSE
+Keywords: agents,ai,ci-cd,llm,regression,testing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Framework :: Pytest
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Testing
+Requires-Python: >=3.10
+Requires-Dist: click>=8.0
+Requires-Dist: jinja2>=3.0
+Requires-Dist: opentelemetry-api>=1.20
+Requires-Dist: opentelemetry-sdk>=1.20
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pytest>=7.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0
+Provides-Extra: all
+Requires-Dist: agentci[anthropic,jsonschema,langgraph,openai]; extra == 'all'
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.20; extra == 'anthropic'
+Provides-Extra: dev
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Provides-Extra: jsonschema
+Requires-Dist: jsonschema>=4.0; extra == 'jsonschema'
+Provides-Extra: langgraph
+Requires-Dist: langgraph>=0.1; extra == 'langgraph'
+Provides-Extra: openai
+Requires-Dist: openai>=1.0; extra == 'openai'
+Description-Content-Type: text/markdown
+
+# AgentCI
+
+Trace-based regression testing for AI agents. Catch semantic drift, tool call changes, and cost spikes before production.
+
+[![Python](https://img.shields.io/pypi/pyversions/agentci)]()
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)]()
+[![CI](https://github.com/agentci-org/agentci/actions/workflows/ci.yml/badge.svg)]()
+[![AGENTS.md](https://img.shields.io/badge/AGENTS.md-supported-blue)](AGENTS.md)
+
+You swap `gpt-4o-mini` for `gpt-4o`. Your support bot starts routing billing questions to the wrong agent. You change a retrieval prompt. Your RAG pipeline silently skips the vector search step. You don't find out until users complain.
+
+AgentCI records what your agent *actually did* — every tool call, LLM invocation, routing decision, and cost — then diffs it against a known-good baseline. When something drifts, you see exactly what changed.
+
+## See It Work
+
+```bash
+# Run your agent's test suite — all green
+$ pytest tests/ -v
+======================== test session starts =========================
+tests/test_routing.py::test_billing_routes_correctly       PASSED
+tests/test_routing.py::test_refund_flow_tool_sequence      PASSED
+tests/test_routing.py::test_cost_under_budget              PASSED
+tests/test_rag.py::test_retrieval_step_executed            PASSED
+tests/test_rag.py::test_no_hallucination                   PASSED
+==================== 5 passed in 0.8s (mock mode) ====================
+
+# Now change one line — swap the model
+-  model = "gpt-4o-mini"
++  model = "gpt-4o"
+
+# Run again — AgentCI catches the drift
+$ pytest tests/test_regression.py -v
+====================== AgentCI Diff Report =======================
+⚠️  ROUTING_CHANGED  "I can't log in and I'm being charged"
+   baseline → Account Agent
+   current  → Billing Agent
+
+⚠️  COST_SPIKE  "Can I get a refund?"
+   baseline: $0.0004  →  current: $0.0025  (6.2x increase)
+
+✅  TOOLS_IDENTICAL  [lookup_invoice, process_refund]
+✅  OUTPUT_SIMILAR   cosine_similarity=0.94
+
+SUMMARY: 1 routing change, 1 cost spike across 5 test cases
+=================================================================
+```
+
+## Quickstart
+
+```bash
+pip install agentguard
+git clone https://github.com/agentci-org/DemoAgents.git
+cd DemoAgents
+make test
+```
+
+You'll see 90+ tests pass across three demo agents — RAG, DevOps, and customer support routing — in under 2 seconds with zero API keys required.
+
+## What It Catches
+
+| What went wrong | How you'd find out today | How AgentCI catches it |
+|----------------|--------------------------|----------------------|
+| Model swap changes routing decisions | User complaints, days later | `ROUTING_CHANGED` diff with exact before/after agents |
+| Prompt edit silently skips a tool call | Manual testing, maybe | `TOOLS_CHANGED` — "vector_search was called, now it's not" |
+| New model costs 6x more per query | Surprise invoice at month-end | `COST_SPIKE` with threshold alerts and `@assert_budget` |
+| RAG retriever returns irrelevant docs | Hallucinated answers in prod | LLM-as-judge assertions: `assert_llm_judge("answer is relevant")` |
+| Guardrail stops firing after refactor | PII leaks through to specialist agent | `guardrails_triggered` trace assertions |
+| Agent responds instead of routing | Support quality drops silently | `assert_handoff_count(expected=1)` catches the missing handoff |
+
+## Works With Your Stack
+
+AgentCI is framework-agnostic. Same assertions, same diff engine, same CLI — regardless of how you built your agent.
+
+| Framework | Integration | Demo |
+|-----------|------------|------|
+| **OpenAI Agents SDK** | Native `AgentCITraceProcessor` — 2 lines to enable | [Support Router](https://github.com/agentci-org/DemoAgents/tree/main/examples/support-router) — multi-agent handoff with guardrails |
+| **LangGraph / LangChain** | `ctx.attach_langgraph_state()` captures conditional edges and tool calls | [RAG Agent](https://github.com/agentci-org/DemoAgents/tree/main/examples/rag-agent) — retrieval + grading + generation pipeline |
+| **Anthropic (raw)** | `AnthropicMocker` for zero-cost replay; native tool_use capture | [DevAgent](https://github.com/agentci-org/DemoAgents/tree/main/examples/dev-agent) — 8-tool sequential repo analysis |
+| **Any Python agent** | Manual `Trace` / `Span` construction for custom frameworks | See [Core Concepts](#core-concepts) below |
+
+All three demo agents run with **zero API keys** using AgentCI's mock system.
+
+## Core Concepts
+
+### Trace & Assert
+
+Every agent run produces a `Trace` — a structured record of LLM calls, tool invocations, handoffs, and guardrail checks.
+
+```python
+from agentci.models import Trace
+
+trace = run_your_agent("I was charged twice")
+
+# What tools did the agent call?
+assert "lookup_invoice" in trace.tool_call_sequence
+assert "process_refund" in trace.tool_call_sequence
+
+# Did it route correctly?
+handoffs = trace.get_handoffs()
+assert handoffs[0].to_agent == "Billing Agent"
+
+# Did it stay under budget?
+assert trace.total_cost_usd < 0.01
+
+# Did guardrails fire when they should?
+assert "pii_guardrail" not in trace.guardrails_triggered
+```
+
+### Golden Baselines
+
+Record a known-good trace. Diff future runs against it.
+
+```bash
+# Record a baseline
+$ agentci record --test-name "billing_flow" --output golden/
+
+# Later, after a change, diff against it
+$ agentci diff --test-name "billing_flow"
+
+# AgentCI reports:
+#   TOOLS_CHANGED — vector_search was called, now it's not
+#   COST_SPIKE — $0.0004 → $0.0025 (6.2x)
+#   ROUTING_CHANGED — Account Agent → Billing Agent
+```
+
+Or use the pytest-native approach with `assert_golden_match`:
+
+```python
+from agentci.assertions import assert_golden_match
+
+def test_billing_regression():
+    trace = run_your_agent("I was charged twice")
+    assert_golden_match(trace, "golden/billing_flow.json")
+```
+
+### Zero-Cost Testing
+
+Mock LLM responses for deterministic, instant, free test runs.
+
+```python
+from agentci.mocks import OpenAIMocker
+from agents import set_default_openai_client
+
+# Define a scripted sequence of tool calls + final response
+mocker = OpenAIMocker([
+    {"tool": "transfer_to_BillingAgent", "arguments": {}},
+    {"tool": "lookup_invoice", "arguments": {"email": "user@test.com"}},
+    {"text": "I found your invoice. The duplicate charge has been refunded."}
+])
+
+# Inject into the OpenAI Agents SDK — no API key needed
+set_default_openai_client(mocker.client)
+
+trace = run_your_agent("I was charged twice")
+assert trace.tool_call_sequence == ["transfer_to_BillingAgent", "lookup_invoice"]
+```
+
+Works the same for Anthropic:
+
+```python
+from agentci.mocks import AnthropicMocker
+
+mocker = AnthropicMocker([
+    {"tool": "search_knowledge_base", "arguments": {"query": "billing"}},
+    {"text": "Here's what I found about billing..."}
+])
+```
+
+## Try Breaking It
+
+Clone the [DemoAgents](https://github.com/agentci-org/DemoAgents) repo and try these:
+
+**Break 1: Remove a specialist agent.** In `examples/support-router/support_router/agents/triage.py`, remove `account_agent` from the `handoffs` list. Run `pytest tests/test_routing.py`. Watch 6 tests fail with: `ROUTING_CHANGED: Expected 'Account Agent', got 'General Agent'`.
+
+**Break 2: Disable retrieval guardrails.** In `examples/support-router/support_router/agents/triage.py`, remove the `input_guardrails` list. Run `pytest tests/test_guardrails.py`. Watch `test_off_topic_blocked` fail: `Expected guardrail 'relevance_guardrail' to trigger, but no guardrails fired.`
+
+**Break 3: Inject bad context.** In `examples/rag-agent/agent.py`, modify the system prompt to remove the "only answer from context" instruction. Run `pytest tests/test_rag.py`. Watch the LLM-as-judge assertion catch the hallucination: `FAILED — Agent used pre-trained knowledge instead of declining.`
+
+## CLI
+
+```bash
+agentci init         # Generate CI config (GitHub Actions + pre-push hooks)
+agentci run          # Run all tests (pytest-compatible)
+agentci record       # Record golden baseline traces
+agentci diff         # Diff current run against baseline
+agentci report       # Generate HTML report from results
+```
+
+## CI/CD
+
+```bash
+agentci init
+```
+
+Generates a GitHub Actions workflow and optional pre-push git hook. Every push runs your agent tests and diffs against golden baselines.
+
+```yaml
+# .github/workflows/agentci.yml (auto-generated)
+name: AgentCI
+on: [push, pull_request]
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - run: pip install -e ".[all]"
+      - run: pytest tests/ -v
+      - run: agentci diff --baseline golden/
+```
+
+## For Coding Agents
+
+If you're a coding agent (Claude Code, Cursor, Codex, Copilot) integrating AgentCI into a project, see [`AGENTS.md`](AGENTS.md) for structured setup instructions, import patterns, and the full assertion API reference.
+
+Quick setup for any agent project:
+1. `pip install agentguard`
+2. Copy the test template from AGENTS.md
+3. Run `agentci init` to generate CI config
+4. Run `agentci run` to execute tests
+
+## Assertions
+
+| Assertion | What it checks |
+|-----------|---------------|
+| `trace.tool_call_sequence` | Ordered list of tool names invoked during the run |
+| `trace.total_cost_usd` | Total LLM cost in USD |
+| `trace.get_handoffs()` | List of agent-to-agent routing decisions |
+| `trace.guardrails_triggered` | Which safety guardrails fired |
+| `trace.agents_involved` | Ordered list of agent names that executed |
+| `assert_golden_match(trace, path)` | Diff against a saved golden baseline |
+| `evaluate_assertion(type="llm_judge")` | LLM-as-judge evaluation of output quality |
+| `evaluate_assertion(type="handoff_target")` | Verify routing destination |
+| `evaluate_assertion(type="handoff_count")` | Verify number of handoffs |
+| `@assert_budget(max_cost=0.10)` | Decorator: fail if run exceeds cost limit |
+| `evaluate_assertion(type="tool_called")` | Verify a specific tool was invoked |
+| `evaluate_assertion(type="output_contains")` | Check output includes expected content |
+| `evaluate_assertion(type="cost_under")` | Check total cost below threshold |
+
+## Diff Report Types
+
+When you diff a current run against a golden baseline, AgentCI flags these change categories:
+
+| Diff Type | Meaning |
+|-----------|---------|
+| `TOOLS_CHANGED` | Different tools were called vs. baseline |
+| `ARGS_CHANGED` | Same tools, but arguments changed |
+| `SEQUENCE_CHANGED` | Tools called in a different order |
+| `COST_SPIKE` | Cost increased beyond threshold |
+| `LATENCY_SPIKE` | Duration increased beyond threshold |
+| `STOP_REASON_CHANGED` | LLM stopped for a different reason |
+| `ROUTING_CHANGED` | Agent handoff went to a different target |
+| `GUARDRAILS_CHANGED` | Different guardrails fired vs. baseline |
+| `OUTPUT_CHANGED` | Final output semantically different |
+| `AVAILABLE_HANDOFFS_CHANGED` | Set of reachable agents changed |
+
+## Status
+
+AgentCI is in **early release** (v0.1.x). The core trace model, diffing engine, assertion library, mock system, and CLI are stable. The API may evolve based on community feedback.
+
+**What's here today:**
+- Trace capture for LangGraph, Anthropic, and OpenAI Agents SDK
+- Golden baseline recording and regression diffing
+- LLM mocking for all three frameworks (zero API keys)
+- LLM-as-judge assertions for subjective output grading
+- Pytest plugin for native integration
+- GitHub Actions generator via `agentci init`
+
+**What's next:**
+- Dashboard UI for trace visualization
+- Trace export (OpenTelemetry format)
+- More framework adapters (CrewAI, AutoGen)
+- MCP server for native coding agent integration
+- Agent Skills distribution for auto-discovery
+- Hosted regression tracking
+
+## Contributing
+
+AgentCI is open source under the Apache 2.0 License. Issues, PRs, and feedback welcome.
+
+If you build an agent and test it with AgentCI, I'd love to hear about it — open an issue or reach out.