notrix-trax 0.1.0__tar.gz

notrix_trax-0.1.0/LICENSE

@@ -0,0 +1,159 @@
+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

notrix_trax-0.1.0/NOTICE

@@ -0,0 +1,9 @@
+Notrix Trax
+Copyright 2026 Notrix LLC
+
+This product includes software developed by Notrix LLC.
+
+Licensed under the Apache License, Version 2.0.
+You may obtain a copy of the License at:
+
+    http://www.apache.org/licenses/LICENSE-2.0

notrix_trax-0.1.0/PKG-INFO

@@ -0,0 +1,314 @@
+Metadata-Version: 2.4
+Name: notrix-trax
+Version: 0.1.0
+Summary: Local-first AI debugging tool for capture, replay, diff, and explanation.
+Author: Notrix
+License: Apache-2.0
+Keywords: ai,debugging,tracing,replay,observability
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: langgraph>=1.1.6
+Dynamic: license-file
+
+# Notrix Trax
+
+**Debug non-deterministic AI workflows — deterministically.**
+
+Trace what happened. Diff what changed. Replay where it broke.
+
+
+```bash
+pip install notrix-trax
+```
+
+---
+
+## Why debugging AI systems is broken
+
+You changed nothing. But your AI system behaves differently.
+
+- different answer
+- different retrieval
+- different agent path
+
+Why?
+
+Logs tell you what ran. They don’t tell you:
+
+- what actually changed
+- where the divergence happened
+- why the outcome is different
+
+AI systems are **non-deterministic and structurally opaque**.
+
+Debugging them shouldn’t be.
+
+---
+
+## What Trax Does
+
+Trax converts raw execution signals into a **canonical execution graph** — a structured, provider-agnostic DAG of steps and edges with stable identity across runs.
+
+From that graph, Notrix trax provides four core operations:
+
+| Operation | What it answers |
+|---|---|
+| `inspect` | What happened in this run, structurally? |
+| `diff` | What changed between run A and run B? |
+| `replay` | Can I simulate replay of the relevant part, safely? |
+| `explain` | What is the evidence-grounded explanation for this failure? |
+
+Every insight is derived from the same canonical graph. Nothing is inferred from display hierarchy or log ordering.
+
+---
+
+## When to use Trax
+
+Use Trax if:
+
+- your LLM output changed and you don’t know why
+- retrieval returns different documents
+- agent behavior is inconsistent
+
+Not for:
+
+- metrics dashboards
+- latency monitoring
+---
+
+## What you get
+
+- **Deterministic execution graph**
+- **Step-level diff between runs**
+- **Replay from failure point**
+- **Evidence-grounded explanations**
+
+All derived from the same canonical structure.
+
+---
+
+## Trax vs Observability Tools
+
+| Feature | Notrix Trax | Observability tools |
+|--------|------|---------------------|
+| Structural diff | ✅ | ❌ |
+| Replay simulation | ✅ | ❌ |
+| Failure explanation | ✅ | ❌ |
+| Logs / traces | ❌ | ✅ |
+
+---
+
+## Quickstart
+
+```bash
+python examples/hero_diff_replay.py
+
+trax list
+trax inspect <run_id>
+trax diff <run_a> <run_b>
+trax explain <run_id>
+trax replay <run_id> --start-at step_4 --stop-at step_8
+```
+
+Trax stores metadata in local SQLite and artifacts on the filesystem (`TRAX_HOME`, default: `~/.trax`). No external services required.
+
+---
+
+## Hero Example
+
+Two runs of your RAG pipeline return different answers. You want to know exactly where they diverged.
+
+```bash
+trax diff run_1 run_2
+```
+
+**See the difference immediately**
+
+![trax diff screenshot](docs/assets/trax-diff.png)
+
+```bash
+trax explain run_2
+```
+![trax explain screenshot](docs/assets/trax-explain.png)
+
+Structural, grounded, reproducible.
+
+---
+
+## Capture
+
+### Drop-in adapters
+
+```python
+from trax.adapters.openai import traced_chat
+from trax.adapters.retrieval import traced_retrieval
+
+docs = traced_retrieval(
+    query="what is trax?",
+    top_k=2,
+    backend="simple_vector",
+    retrieve=lambda **_: [{"id": "doc-1", "text": "Trax debugs AI runs."}],
+)
+
+response = traced_chat(
+    model="gpt-4.1-mini",
+    messages=[{"role": "user", "content": "Summarize Trax."}],
+    call=lambda **_: {"output_text": "Trax is a local-first AI debugger."},
+)
+```
+
+### Manual SDK
+
+```python
+from trax import run, step, traced_step
+
+@traced_step("prepare", attributes={"semantic_type": "transform"})
+def prepare_question(text: str) -> dict[str, str]:
+    return {"normalized_question": text.strip().lower()}
+
+with run("my-flow", input={"question": "What does Trax do?"}):
+    question = prepare_question("What does Trax do?")
+    with step("answer", input=question, attributes={"semantic_type": "llm"}) as s:
+        s.set_output({"answer": "Trax debugs AI workflows locally."})
+```
+
+### LangGraph (first-class support)
+
+Invocation-level and node-level tracing with no dependency on internal callbacks. Works with real compiled graphs.
+
+```python
+from trax.langgraph import traced_invoke
+from langgraph.graph import StateGraph
+
+graph = StateGraph(MyState)
+# ... define nodes and edges ...
+compiled = graph.compile()
+
+result = traced_invoke(compiled, {"question": "What does Trax do?"})
+```
+
+---
+
+## CLI Reference
+
+```bash
+trax list                              # list all captured runs
+trax inspect <run_id>                  # inspect a run's canonical graph
+trax diff <run_id_1> <run_id_2>        # structural diff between two runs
+trax replay <run_id>                   # simulate replay of a run under persisted safety policy
+trax replay <run_id> --start-at <step> --stop-at <step>  # partial replay
+trax explain <run_id>                  # evidence-grounded failure explanation
+trax import-otel trace.json            # import an OpenTelemetry trace
+```
+
+---
+
+## How It Works
+
+Trax builds a **canonical execution graph** — not a trace, not a log, not a span tree.
+
+```
+Capture → Collect → Normalize → Graph → Diff / Detect / Replay → Explain
+```
+
+The key properties that make this useful for debugging:
+
+**Stable step identity.** The same logical step normalizes to the same canonical meaning across runs. This makes structural diffing possible — you're comparing the same thing, not two different representations of it.
+
+**Edge-driven structure.** Relationships between steps are derived from persisted graph edges and deterministic fallback rules. There are no implicit structural relationships from display hierarchy.
+
+**Provider-agnostic adapters.** Different framework or provider integrations emit signals that normalize into the same canonical step model, so diffs and replay stay meaningful across tool boundaries.
+
+**Display hierarchy is not structure.** Scope hints and nesting from adapters are stored as metadata only. They influence how things look, not how the graph is built.
+
+---
+
+## Core Concepts
+
+| Concept | Definition |
+|---|---|
+| **Run** | A single captured execution instance |
+| **Step** | A canonical, normalized unit of work (e.g., `llm:call`, `retrieval:query`) |
+| **Edge** | A directional canonical relationship between steps |
+| **Artifact** | Input/output data associated with a step |
+| **Failure** | A detected issue localized to a specific step in the graph |
+
+Step names follow the format `<domain>:<operation>`. Current surfaced domains include `llm`, `retrieval`, `tool`, `agent`, `reasoning`, `transform`, `io`, `rerank`, and `unknown`.
+
+---
+
+## Examples
+
+| Example | What it demonstrates |
+|---|---|
+| `examples/basic_capture.py` | Minimal manual SDK capture |
+| `examples/rag_failure/` | Retrieval divergence across two runs |
+| `examples/agent_loop/` | Structural path divergence in an agent loop |
+| `examples/langgraph_basic.py` | Real LangGraph execution with node-level tracing |
+
+```bash
+python examples/hero_diff_replay.py
+```
+
+---
+
+## Development
+
+```bash
+git clone https://github.com/notrix-dev/notrix-trax.git
+cd notrix-trax
+pip install -e .
+pip install -r requirements.txt
+pytest
+```
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for how to build adapters, improve the core system, or contribute to the spec.
+
+---
+
+## Project Structure
+
+```
+trax/
+  adapters/       # capture layer — framework integrations
+  normalize/      # canonical step meaning
+  graph/          # structural edge construction and validation
+  replay/         # deterministic replay engine
+  diff/           # two-run structural comparison
+  detect/         # single-run failure detection
+  cli/            # projection layer
+
+docs/             # system and subsystem specifications
+examples/         # runnable demos
+```
+
+---
+
+## Spec-Driven Design
+
+Trax is architecture-first. The system behavior is defined in a set of layered specifications:
+
+- `docs/system-spec.md` — authoritative system contract
+- `docs/spec-graph.md` — canonical graph model
+- `docs/spec-normalizer.md` — step semantics and naming
+- `docs/spec-diff-detect.md` — diff and detect contract
+- `docs/spec-replay.md` — replay contract
+- `docs/spec-adapter.md` — adapter contract
+
+If you want to understand *why* the system is designed the way it is, the specs are the place to start.
+
+---
+
+## License
+
+[Apache License 2.0](LICENSE)