agentprdiff 0.1.0__tar.gz → 0.2.1__tar.gz

{agentprdiff-0.1.0 → agentprdiff-0.2.1}/.gitignore

@@ -26,7 +26,8 @@ env/
 .vscode/
 *.swp
 
-# agentguard runtime
-# Users SHOULD commit .agentguard/baselines; they should NOT commit run artifacts.
-.agentguard/runs/
-.agentguard/cache/
+# agentprdiff runtime
+# Users SHOULD commit .agentprdiff/baselines; they should NOT commit run artifacts.
+.agentprdiff/runs/
+.agentprdiff/cache/
+.pypirc

agentprdiff-0.2.1/CHANGELOG.md

@@ -0,0 +1,129 @@
+# Changelog
+
+All notable changes to `agentprdiff` are documented in this file. Originally
+prototyped under the name `tracediff`; renamed before first public release.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.2.1] — 2026-04-26
+
+### Changed
+
+- README links to `AGENTS.md`, `docs/adapters.md`, `docs/ai-driven-adoption.md`,
+  `docs/suite-layout.md`, `docs/ci-integration.md`, `LICENSE`, and `CHANGELOG.md`
+  are now absolute GitHub URLs instead of relative paths. PyPI's project page
+  and Libraries.io render the README but cannot resolve relative repo paths;
+  the previous links rendered as broken from those surfaces. Absolute URLs
+  fix the click-through from PyPI / Libraries.io directly to the docs on
+  GitHub.
+- Status section refreshed: 0.2.x is the current alpha line; OpenAI and
+  Anthropic SDK adapters are now shipped (previously listed as 0.2 roadmap).
+  LangChain/LangGraph adapters and the JS companion package moved to the
+  0.3 roadmap.
+
+### Fixed
+
+- Wheel metadata now emits a separate `Author:` header in addition to
+  `Author-email:`. Previously, the PEP 621 `authors = [{ name = ..., email = ... }]`
+  form generated only `Author-email: "Name" <email>`, which downstream
+  parsers like pypistats.org could not read (showing "Author: None").
+  Splitting `authors` into a name-only entry plus an email-only entry,
+  and adding a parallel `maintainers` field, makes the package author
+  display correctly across PyPI, Libraries.io, and pypistats.
+
+## [0.2.0] — 2026-04-26
+
+### Added
+
+- **SDK adapters** for the two dominant agent toolchains, eliminating the need
+  for manual `Trace` instrumentation:
+  - `agentprdiff.adapters.openai.instrument_client` — context manager that
+    monkey-patches `client.chat.completions.create` for the duration of one
+    agent call. Records each invocation as an `LLMCall` (provider, model,
+    input messages, output text, tool calls, tokens, cost, latency) and
+    restores the original on exit. Works with **OpenAI, Groq, Gemini's
+    OpenAI-compatible endpoint, OpenRouter, Ollama, vLLM, Together,
+    Fireworks, DeepInfra**, and any other SDK that follows the OpenAI client
+    shape.
+  - `agentprdiff.adapters.anthropic.instrument_client` — equivalent for the
+    Anthropic Messages API (`client.messages.create`). Handles the
+    content-block response shape (text + `tool_use` blocks) and the
+    Messages-API token field names.
+  - `instrument_tools(tool_map, trace)` — wraps a dict of callables so each
+    invocation records a `ToolCall` with name, arguments, result, latency,
+    and any raised exception. Shared between both adapters.
+  - `agentprdiff.adapters.pricing` — curated model→price table for cost
+    estimation, with `register_prices()` and per-call `prices=` overrides.
+    Unknown models record `cost_usd=0.0` and emit a single `RuntimeWarning`
+    per process so missing pricing is loud rather than silent.
+- Documentation: `docs/adapters.md` (full reference) and
+  `docs/adapters-vercel.md` (manual integration recipe for the Vercel AI
+  SDK, which is JS-only and lives in a future companion package).
+- `AGENTS.md` at the repo root — an instruction set written for AI
+  coding agents (Claude Code, Cursor, Aider, etc.) that have been asked
+  to add `agentprdiff` to a codebase. Covers codebase discovery,
+  contract identification, wrap-the-agent recipes (OpenAI / Anthropic /
+  custom), stub patterns, suite scaffolding, baseline recording, CI
+  wiring, common pitfalls, and a validation checklist. Optimized for
+  AI-agent-driven adoption with copy-paste templates.
+- `docs/ai-driven-adoption.md` — human-facing companion to AGENTS.md.
+  Three prompt templates (minimum viable / recommended / contract-driven)
+  for adopters using Claude Code / Cursor / Aider, plus a sample
+  first-session transcript and tips for working with the AI agent
+  through the adoption flow.
+- `docs/suite-layout.md` — canonical reference for the suite directory
+  structure. Lists each file (`suites/<project>.py`, `_eval_agent.py`,
+  `_stubs.py`, baselines, CI workflow, etc.), classifies them as
+  mandatory / recommended / optional, and specifies what each must
+  and must not contain. Cross-referenced from AGENTS.md and the
+  validation checklist.
+
+### Changed
+
+- The suite loader now inserts the current working directory onto
+  `sys.path` in addition to the suite file's parent directory. Adopters
+  who run `agentprdiff record suites/foo.py` from their project root no
+  longer have to manually patch `sys.path` to import their own modules
+  (e.g. `from agent.agent import ...`, `from config import ...`).
+  Both insertions are reverted after the suite loads, so no path leakage
+  between runs.
+
+### Notes
+
+- The base `pip install agentprdiff` does **not** require the `openai` or
+  `anthropic` packages. The adapters operate on a client object's shape,
+  not on imported SDK modules — so installing only the SDKs you actually
+  use keeps the dependency footprint small. Optional extras are still
+  declared (`agentprdiff[openai]`, `agentprdiff[anthropic]`) for adopters
+  who prefer to pin the SDK version alongside agentprdiff itself.
+
+## [0.1.0] — 2026-04-22
+
+Initial public release.
+
+### Added
+
+- Core `Suite` / `Case` / `Trace` model for defining agent regression tests.
+- Deterministic graders: `contains`, `contains_any`, `regex_match`, `tool_called`,
+  `tool_sequence`, `output_length_lt`, `latency_lt_ms`, `cost_lt_usd`,
+  `no_tool_called`.
+- Semantic grader (`semantic`) with a pluggable `judge` callable and built-in
+  fake judge for CI environments without API keys.
+- Baseline store (JSON files under `.agentprdiff/baselines/`) designed to be
+  committed to version control.
+- Trace diff engine producing a structured `TraceDelta` (assertion pass/fail
+  changes, cost delta, latency delta, tool-call sequence changes, output
+  change).
+- CLI: `agentprdiff init`, `agentprdiff record`, `agentprdiff check`, `agentprdiff diff`.
+- Rich-formatted terminal reporter and machine-readable JSON reporter for CI.
+- Quickstart example with a mock agent that runs without any API keys.
+- Pytest test suite covering graders, runner, differ, store, and CLI smoke.
+- GitHub Actions CI workflow.
+
+### Known limitations
+
+- Only a manual instrumentation API for provider SDKs is shipped in 0.1.0.
+  Drop-in wrappers for OpenAI / Anthropic / Vercel AI SDK are planned for 0.2.
+- The semantic grader's built-in judge supports OpenAI and Anthropic via user-
+  supplied API keys; hosted judge endpoints are not yet offered.

{agentprdiff-0.1.0 → agentprdiff-0.2.1}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: agentprdiff
-Version: 0.1.0
+Version: 0.2.1
 Summary: Guard your LLM agents in CI. Snapshot tests that catch behavioral regressions when models, prompts, or vendors change.
 Project-URL: Homepage, https://github.com/vnageshwaran-de/agentprdiff
 Project-URL: Documentation, https://github.com/vnageshwaran-de/agentprdiff#readme
 Project-URL: Issues, https://github.com/vnageshwaran-de/agentprdiff/issues
 Project-URL: Repository, https://github.com/vnageshwaran-de/agentprdiff
-Author-email: Vinoth Nageshwaran <vnageshwaran@gmail.com>
+Author: Vinoth Nageshwaran
+Author-email: vnageshwaran@gmail.com
+Maintainer-email: Vinoth Nageshwaran <vnageshwaran@gmail.com>
 License: MIT
 License-File: LICENSE
 Keywords: agent,ci,evaluation,llm,observability,regression-testing,snapshot-testing
@@ -48,7 +50,9 @@ pip install agentprdiff
 [![CI](https://github.com/vnageshwaran-de/agentprdiff/actions/workflows/ci.yml/badge.svg)](https://github.com/vnageshwaran-de/agentprdiff/actions/workflows/ci.yml)
 [![PyPI](https://img.shields.io/pypi/v/agentprdiff.svg)](https://pypi.org/project/agentprdiff/)
 [![Python](https://img.shields.io/pypi/pyversions/agentprdiff.svg)](https://pypi.org/project/agentprdiff/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/vnageshwaran-de/agentprdiff/blob/main/LICENSE)
+
+> **Adopting with an AI coding agent?** Point Claude Code, Cursor, Aider, or any agentic IDE at [`AGENTS.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/AGENTS.md) — a step-by-step adoption playbook the agent reads directly. Humans driving the adoption: see [`docs/ai-driven-adoption.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/ai-driven-adoption.md) for copy-paste prompt templates. The canonical file layout — what's mandatory, what's recommended, what's optional — is at [`docs/suite-layout.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/suite-layout.md).
 
 ## Why
 
@@ -100,6 +104,7 @@ That's the whole product. Four CLI commands. One Python file. Zero framework loc
 - **Diff engine** — per-case `TraceDelta` with assertion pass/fail changes, cost delta, latency delta, tool-sequence changes, and a unified output diff.
 - **CI-ready CLI** — exit 1 on regression, `--json-out` for artifact archiving, Rich-formatted terminal output.
 - **Zero SDK lock-in** — works with OpenAI, Anthropic, Gemini, Bedrock, LangChain, LangGraph, LlamaIndex, Vercel AI SDK, custom wrappers — if you can wrap your agent in a function, `agentprdiff` can test it.
+- **One-line SDK adapters** — `with instrument_client(client) as trace:` automatically records every LLM and tool call when you're on the OpenAI Python SDK (or any OpenAI-compatible provider — Groq / Gemini / OpenRouter / Ollama / vLLM) or the Anthropic SDK. No manual `Trace` wiring required.
 
 ## How it compares
 
@@ -124,7 +129,34 @@ This is the same loop as Jest snapshot tests or VCR cassettes — applied to LLM
 
 ## Instrumenting your agent
 
-`agentprdiff` doesn't monkey-patch anything. Your agent returns `(output, Trace)`:
+You have two paths. Most agents need the first.
+
+### Option A — SDK adapters (zero manual work)
+
+If your agent uses the OpenAI Python SDK (or any OpenAI-compatible provider — Groq, Gemini, OpenRouter, Ollama, vLLM, Together, Fireworks, DeepInfra) or the Anthropic SDK, the SDK adapter captures every model and tool call automatically:
+
+```python
+from openai import OpenAI
+from agentprdiff.adapters.openai import instrument_client, instrument_tools
+
+TOOL_MAP = {"lookup_order": lookup_order, "send_email": send_email}
+
+def my_agent(query: str):
+    client = OpenAI()
+    with instrument_client(client) as trace:
+        tools = instrument_tools(TOOL_MAP, trace)
+        # ... your existing tool-calling loop, untouched ...
+        # the only swap: TOOL_MAP[fn](**args) → tools[fn](**args)
+        return final_text, trace
+```
+
+The patch is scoped to the specific client instance and reversed when the `with` block exits — no global SDK state is touched. Anthropic adopters use `agentprdiff.adapters.anthropic` with the same shape.
+
+See [`docs/adapters.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/adapters.md) for the full reference, including pricing overrides, custom provider tags, and recipes for nested agents.
+
+### Option B — Manual instrumentation
+
+If you're not on either SDK, or you want full control, build the `Trace` yourself — `agentprdiff` doesn't require any monkey-patching:
 
 ```python
 from agentprdiff import Trace, LLMCall, ToolCall
@@ -168,7 +200,7 @@ jobs:
         with: { name: agentprdiff, path: artifacts/ }
 ```
 
-See [`docs/ci-integration.md`](./docs/ci-integration.md) for GitLab, CircleCI, and Buildkite.
+See [`docs/ci-integration.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/ci-integration.md) for GitLab, CircleCI, and Buildkite.
 
 ## Quickstart
 
@@ -191,10 +223,10 @@ agentprdiff check suite.py    # exit 1; see the diff
 
 ## Status
 
-`agentprdiff` is **alpha** (0.1.0). The core model and CLI are stable; provider-specific SDK wrappers and a LangChain/LangGraph integration are on the 0.2 roadmap. See [`CHANGELOG.md`](./CHANGELOG.md).
+`agentprdiff` is **alpha** (0.2.x). The core model, CLI, and OpenAI / Anthropic SDK adapters are stable. LangChain/LangGraph adapters and a JS companion package for the Vercel AI SDK are on the 0.3 roadmap. See [`CHANGELOG.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/CHANGELOG.md).
 
 Feedback, bug reports, and PRs extremely welcome. Open an issue or @ me.
 
 ## License
 
-MIT. See [`LICENSE`](./LICENSE).
+MIT. See [`LICENSE`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/LICENSE).

{agentprdiff-0.1.0 → agentprdiff-0.2.1}/README.md

@@ -11,7 +11,9 @@ pip install agentprdiff
 [![CI](https://github.com/vnageshwaran-de/agentprdiff/actions/workflows/ci.yml/badge.svg)](https://github.com/vnageshwaran-de/agentprdiff/actions/workflows/ci.yml)
 [![PyPI](https://img.shields.io/pypi/v/agentprdiff.svg)](https://pypi.org/project/agentprdiff/)
 [![Python](https://img.shields.io/pypi/pyversions/agentprdiff.svg)](https://pypi.org/project/agentprdiff/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/vnageshwaran-de/agentprdiff/blob/main/LICENSE)
+
+> **Adopting with an AI coding agent?** Point Claude Code, Cursor, Aider, or any agentic IDE at [`AGENTS.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/AGENTS.md) — a step-by-step adoption playbook the agent reads directly. Humans driving the adoption: see [`docs/ai-driven-adoption.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/ai-driven-adoption.md) for copy-paste prompt templates. The canonical file layout — what's mandatory, what's recommended, what's optional — is at [`docs/suite-layout.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/suite-layout.md).
 
 ## Why
 
@@ -63,6 +65,7 @@ That's the whole product. Four CLI commands. One Python file. Zero framework loc
 - **Diff engine** — per-case `TraceDelta` with assertion pass/fail changes, cost delta, latency delta, tool-sequence changes, and a unified output diff.
 - **CI-ready CLI** — exit 1 on regression, `--json-out` for artifact archiving, Rich-formatted terminal output.
 - **Zero SDK lock-in** — works with OpenAI, Anthropic, Gemini, Bedrock, LangChain, LangGraph, LlamaIndex, Vercel AI SDK, custom wrappers — if you can wrap your agent in a function, `agentprdiff` can test it.
+- **One-line SDK adapters** — `with instrument_client(client) as trace:` automatically records every LLM and tool call when you're on the OpenAI Python SDK (or any OpenAI-compatible provider — Groq / Gemini / OpenRouter / Ollama / vLLM) or the Anthropic SDK. No manual `Trace` wiring required.
 
 ## How it compares
 
@@ -87,7 +90,34 @@ This is the same loop as Jest snapshot tests or VCR cassettes — applied to LLM
 
 ## Instrumenting your agent
 
-`agentprdiff` doesn't monkey-patch anything. Your agent returns `(output, Trace)`:
+You have two paths. Most agents need the first.
+
+### Option A — SDK adapters (zero manual work)
+
+If your agent uses the OpenAI Python SDK (or any OpenAI-compatible provider — Groq, Gemini, OpenRouter, Ollama, vLLM, Together, Fireworks, DeepInfra) or the Anthropic SDK, the SDK adapter captures every model and tool call automatically:
+
+```python
+from openai import OpenAI
+from agentprdiff.adapters.openai import instrument_client, instrument_tools
+
+TOOL_MAP = {"lookup_order": lookup_order, "send_email": send_email}
+
+def my_agent(query: str):
+    client = OpenAI()
+    with instrument_client(client) as trace:
+        tools = instrument_tools(TOOL_MAP, trace)
+        # ... your existing tool-calling loop, untouched ...
+        # the only swap: TOOL_MAP[fn](**args) → tools[fn](**args)
+        return final_text, trace
+```
+
+The patch is scoped to the specific client instance and reversed when the `with` block exits — no global SDK state is touched. Anthropic adopters use `agentprdiff.adapters.anthropic` with the same shape.
+
+See [`docs/adapters.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/adapters.md) for the full reference, including pricing overrides, custom provider tags, and recipes for nested agents.
+
+### Option B — Manual instrumentation
+
+If you're not on either SDK, or you want full control, build the `Trace` yourself — `agentprdiff` doesn't require any monkey-patching:
 
 ```python
 from agentprdiff import Trace, LLMCall, ToolCall
@@ -131,7 +161,7 @@ jobs:
         with: { name: agentprdiff, path: artifacts/ }
 ```
 
-See [`docs/ci-integration.md`](./docs/ci-integration.md) for GitLab, CircleCI, and Buildkite.
+See [`docs/ci-integration.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/docs/ci-integration.md) for GitLab, CircleCI, and Buildkite.
 
 ## Quickstart
 
@@ -154,10 +184,10 @@ agentprdiff check suite.py    # exit 1; see the diff
 
 ## Status
 
-`agentprdiff` is **alpha** (0.1.0). The core model and CLI are stable; provider-specific SDK wrappers and a LangChain/LangGraph integration are on the 0.2 roadmap. See [`CHANGELOG.md`](./CHANGELOG.md).
+`agentprdiff` is **alpha** (0.2.x). The core model, CLI, and OpenAI / Anthropic SDK adapters are stable. LangChain/LangGraph adapters and a JS companion package for the Vercel AI SDK are on the 0.3 roadmap. See [`CHANGELOG.md`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/CHANGELOG.md).
 
 Feedback, bug reports, and PRs extremely welcome. Open an issue or @ me.
 
 ## License
 
-MIT. See [`LICENSE`](./LICENSE).
+MIT. See [`LICENSE`](https://github.com/vnageshwaran-de/agentprdiff/blob/main/LICENSE).

agentprdiff-0.2.1/examples/regression-tour/README.md

@@ -0,0 +1,140 @@
+# Regression tour
+
+A complete walkthrough of every grader and every failure mode in `agentprdiff`. Runs without API keys (uses `fake_judge` for the semantic grader so no OpenAI/Anthropic key is required).
+
+## What this exercises
+
+- All 10 deterministic and semantic graders: `contains`, `contains_any`, `regex_match`, `tool_called`, `tool_sequence`, `no_tool_called`, `output_length_lt`, `latency_lt_ms`, `cost_lt_usd`, `semantic`.
+- All 6 regression scenarios the differ can detect: output drift, extra tool, missing tool, tool reordering, latency regression, cost regression.
+- The Rich terminal reporter and exit-code behavior used in CI.
+
+## A note on invocation
+
+The commands below use `agentprdiff` directly. If pip's user-script directory isn't on your PATH, substitute `python3 -m agentprdiff.cli` everywhere — both forms are equivalent.
+
+## Setup (one-time)
+
+```bash
+cd examples/regression-tour
+agentprdiff init                    # creates the .agentprdiff/ scaffolding
+agentprdiff record suite.py         # captures the baseline trace
+```
+
+You should see baselines written under `.agentprdiff/baselines/`. In a real project these get committed to git — that's the whole point of agentprdiff.
+
+## Happy path
+
+```bash
+agentprdiff check suite.py
+echo "exit: $?"                     # 0
+```
+
+All three cases pass with no diff against the recorded baseline.
+
+## Regression scenarios
+
+Each command below injects one specific regression by setting `MODE`. Every one should fail with a clear diff and a non-zero exit code.
+
+### 1. Output text drifted
+
+```bash
+MODE=output_changed agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+The agent's refund response changes from the baseline phrasing to "Refund initiated. Please allow 7–10 business days for processing." That trips:
+
+- `contains("refund")` — still passes (the new text mentions refund)
+- `contains_any(["business days", "card", "processed"])` — still passes
+- `regex_match(r"\$\d+\.\d{2}")` — **fails** (no dollar amount in the new output)
+- `output_length_lt(500)` — still passes
+- `semantic(...)` — likely **fails** depending on judge backend
+
+The terminal reporter prints a unified output diff so the reviewer can see exactly what changed.
+
+### 2. Extra tool call
+
+```bash
+MODE=tool_added agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+The agent calls `check_inventory` after `lookup_order`. That trips:
+
+- `tool_sequence(["lookup_order"])` — **fails** (sequence is now `["lookup_order", "check_inventory"]`)
+- `no_tool_called("check_inventory")` — **fails**
+
+### 3. Missing tool call
+
+```bash
+MODE=tool_removed agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+The agent never calls `lookup_order` and produces a fallback "trouble looking up your order" response. That trips:
+
+- `tool_called("lookup_order")` — **fails**
+- `tool_sequence(["lookup_order"])` — **fails**
+- `contains("refund")` — **fails** (output text changed)
+- `regex_match(r"\$\d+\.\d{2}")` — **fails**
+
+### 4. Tool order swapped
+
+```bash
+MODE=tool_reordered agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+The agent calls `check_inventory` *before* `lookup_order`. Same tools, wrong order:
+
+- `tool_sequence(["lookup_order"])` — **fails** (sequence is `["check_inventory", "lookup_order"]`)
+- `no_tool_called("check_inventory")` — **fails**
+
+### 5. Latency regression
+
+```bash
+MODE=latency_regressed agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+Planner LLM call jumps from 180 ms to 8 s, blowing past the 5 s cap:
+
+- `latency_lt_ms(5_000)` — **fails**
+
+The reporter shows the latency delta against baseline.
+
+### 6. Cost regression
+
+```bash
+MODE=cost_regressed agentprdiff check suite.py
+echo "exit: $?"                     # non-zero
+```
+
+Responder cost jumps from $0.0008 to $0.10 per call:
+
+- `cost_lt_usd(0.01)` — **fails**
+
+The reporter shows the cost delta against baseline.
+
+## Run them all back to back
+
+```bash
+./tour.sh
+```
+
+Runs every scenario with banners, prints exit codes, and gives you a one-screen overview of what the tool detects.
+
+## Resetting the baseline
+
+If you want to make the new behavior the new baseline (e.g., you intentionally changed the agent), re-record:
+
+```bash
+MODE=output_changed agentprdiff record suite.py     # baseline now matches the changed output
+agentprdiff check suite.py                          # passes against the new baseline
+```
+
+This is the workflow you'll use in real projects when a model upgrade or prompt change is intentional.
+
+## Why this matters
+
+The point of `agentprdiff` is that every one of these scenarios should be caught **before** the change reaches production. Run `agentprdiff check` in CI on every PR and the merge is blocked when behavior changes — same as `pytest` blocks merges when tests break.

{agentprdiff-0.1.0 → agentprdiff-0.2.1}/pyproject.toml

@@ -4,12 +4,16 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agentprdiff"
-version = "0.1.0"
+version = "0.2.1"
 description = "Guard your LLM agents in CI. Snapshot tests that catch behavioral regressions when models, prompts, or vendors change."
 readme = "README.md"
 requires-python = ">=3.10"
 license = { text = "MIT" }
-authors = [{ name = "Vinoth Nageshwaran", email = "vnageshwaran@gmail.com" }]
+authors = [
+    { name = "Vinoth Nageshwaran" },
+    { email = "vnageshwaran@gmail.com" },
+]
+maintainers = [{ name = "Vinoth Nageshwaran", email = "vnageshwaran@gmail.com" }]
 keywords = [
     "llm",
     "agent",

{agentprdiff-0.1.0 → agentprdiff-0.2.1}/src/agentprdiff/__init__.py

@@ -30,6 +30,22 @@ Run from the shell::
     agentprdiff init
     agentprdiff record path/to/my_suite.py     # save baselines
     agentprdiff check  path/to/my_suite.py     # diff against baselines; exit 1 on regression
+
+If your agent already uses the OpenAI Python SDK (or any OpenAI-compatible
+provider — Groq, Gemini, OpenRouter, Ollama, vLLM) or the Anthropic SDK, the
+SDK adapters capture every model and tool call automatically, no manual Trace
+wiring required::
+
+    from agentprdiff.adapters.openai import instrument_client, instrument_tools
+
+    def my_agent(query):
+        client = OpenAI(...)
+        with instrument_client(client) as trace:
+            tools = instrument_tools(TOOL_MAP, trace)
+            # ... your existing tool-calling loop, untouched ...
+            return final_text, trace
+
+See ``docs/adapters.md`` for the full reference.
 """
 
 from __future__ import annotations
@@ -51,7 +67,7 @@ from .differ import AssertionChange, TraceDelta, diff_traces
 from .runner import CaseReport, Runner, RunReport
 from .store import BaselineStore
 
-__version__ = "0.1.0"
+__version__ = "0.2.1"
 
 __all__ = [
     # core

agentprdiff-0.2.1/src/agentprdiff/adapters/__init__.py

@@ -0,0 +1,43 @@
+"""SDK adapters for agentprdiff.
+
+The adapters take an agent that uses a real LLM SDK (OpenAI, Anthropic, or any
+OpenAI-compatible provider like Groq, Gemini's openai-compat endpoint,
+OpenRouter, Ollama, or vLLM) and capture every model call as an `LLMCall` on a
+`Trace` — without forcing the user to rewrite their agent loop.
+
+The pattern is::
+
+    from agentprdiff.adapters.openai import instrument_client, instrument_tools
+
+    def my_agent(query: str):
+        client = OpenAI(...)
+        with instrument_client(client) as trace:
+            tools = instrument_tools(TOOL_MAP, trace)
+            # ... user's existing tool-calling loop, untouched ...
+            return final_text, trace
+
+Submodules are imported lazily so the base `agentprdiff` install doesn't pull
+in `openai` / `anthropic` unless the user opts in via the extras::
+
+    pip install "agentprdiff[openai]"
+    pip install "agentprdiff[anthropic]"
+
+See `docs/adapters.md` for the full reference.
+"""
+
+from __future__ import annotations
+
+# Re-export pricing helpers — these are pure-Python and have no SDK dependency.
+from .pricing import (
+    DEFAULT_PRICES,
+    PriceTable,
+    estimate_cost_usd,
+    register_prices,
+)
+
+__all__ = [
+    "DEFAULT_PRICES",
+    "PriceTable",
+    "estimate_cost_usd",
+    "register_prices",
+]