journeygraph 0.1.1__tar.gz

journeygraph-0.1.1/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.

journeygraph-0.1.1/PKG-INFO

@@ -0,0 +1,285 @@
+Metadata-Version: 2.4
+Name: journeygraph
+Version: 0.1.1
+Summary: Local-first graph analytics for AI agent traces and event data
+Author: German Gerken
+License-Expression: Apache-2.0
+Project-URL: Documentation, https://github.com/GermanGerken/journeygraph#readme
+Project-URL: Issues, https://github.com/GermanGerken/journeygraph/issues
+Project-URL: Repository, https://github.com/GermanGerken/journeygraph
+Project-URL: Changelog, https://github.com/GermanGerken/journeygraph/blob/main/CHANGELOG.md
+Project-URL: Security, https://github.com/GermanGerken/journeygraph/security/policy
+Keywords: ai-agents,graph-analytics,journey-analysis,llm-observability,opentelemetry,path-mining,trace-analysis
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: parquet
+Requires-Dist: pyarrow<26,>=25.0.0; extra == "parquet"
+Provides-Extra: dev
+Requires-Dist: bandit<2,>=1.8; extra == "dev"
+Requires-Dist: build<2,>=1.5; extra == "dev"
+Requires-Dist: detect-secrets<2,>=1.5; extra == "dev"
+Requires-Dist: hypothesis<7,>=6.158; extra == "dev"
+Requires-Dist: jsonschema<5,>=4.26; extra == "dev"
+Requires-Dist: mypy<3,>=2.3; extra == "dev"
+Requires-Dist: pip-audit<3,>=2.10; extra == "dev"
+Requires-Dist: pytest<10,>=9.1; extra == "dev"
+Requires-Dist: pytest-cov<8,>=7.1; extra == "dev"
+Requires-Dist: ruff<1,>=0.15; extra == "dev"
+Requires-Dist: twine<7,>=6.2; extra == "dev"
+Provides-Extra: mutation
+Requires-Dist: mutmut<4,>=3.6; extra == "mutation"
+Dynamic: license-file
+
+# JourneyGraph
+
+Local-first graph analytics for recurring paths, loops, failures, and outcomes across
+AI-agent traces and event data.
+
+> **JourneyGraph does not collect traces. It analyzes the traces and event exports you already
+> have.** Core analysis runs locally, needs no account or API key, and sends no telemetry.
+
+![JourneyGraph demo graph](docs/assets/demo-graph.svg)
+
+Tracing tools help inspect one execution. JourneyGraph answers population-level questions:
+Which paths recur across many executions? Where do agents retry, loop, fail, hand off, or drop
+off? Which exact paths are associated with outcomes, and how do latency, token use, or cost
+differ globally or across retained cohorts?
+
+JourneyGraph 0.1 is an early alpha with a deliberately narrow, tested contract. It turns
+canonical JSONL, CSV, optional Parquet, or one supported OTLP/JSON request shape into a
+deterministic aggregate graph, machine-readable analysis, normalized events, static HTML, and
+standalone SVG.
+
+## Five-minute quickstart
+
+Python 3.11 or later is required. From a fresh checkout, this single setup-and-demo command
+installs the standard-library runtime core and generates a complete synthetic report:
+
+```bash
+git clone https://github.com/GermanGerken/journeygraph.git
+cd journeygraph
+python3 -m venv .venv && . .venv/bin/activate && python -m pip install . && journeygraph demo --output-dir journeygraph-demo
+```
+
+Open `journeygraph-demo/report.html` in a browser. The command also writes:
+
+```text
+journeygraph-demo/
+├── analysis.json
+├── demo-traces.jsonl
+├── graph.svg
+├── normalized.jsonl
+└── report.html
+```
+
+The packaged demo is deterministic and entirely synthetic. Its current output contains 45
+events across 9 traces, 13 aggregate nodes, 19 unique transitions, 2 retry categories, and 3
+exact return-loop sequences. Outcomes are 5 successes, 2 failures, 1 handoff, and 1 drop-off.
+
+## Analyze your own export
+
+Canonical JSON Lines contains one operation per line:
+
+```json
+{"schema_version":"1.0","trace_id":"trace-1","step_id":"request","timestamp":"2026-07-21T08:00:00Z","operation_type":"request","component":"user_request","duration_ms":4,"status":"ok"}
+{"schema_version":"1.0","trace_id":"trace-1","step_id":"answer","parent_step_id":"request","timestamp":"2026-07-21T08:00:00.125Z","operation_type":"outcome","component":"completed","duration_ms":1,"status":"ok","outcome":"success"}
+```
+
+Validate first, then produce all four analysis artifacts:
+
+```bash
+journeygraph validate traces.jsonl
+journeygraph analyze traces.jsonl --output-dir journeygraph-report
+```
+
+A compact part of `analysis.json` looks like this for the packaged demo:
+
+```json
+{
+  "schema_version": "1.0",
+  "totals": {
+    "events": 45,
+    "nodes": 13,
+    "traces": 9,
+    "transitions": 36,
+    "unique_transitions": 19
+  },
+  "outcomes": {
+    "counts": {
+      "dropoff": 1,
+      "failure": 2,
+      "handoff": 1,
+      "success": 5,
+      "unknown": 0
+    }
+  }
+}
+```
+
+Use `--cohort-key environment` to compare retained operational cohorts. Use repeatable
+`--allow-metadata-key KEY` options only for additional non-sensitive operational fields.
+Sensitive-key rules remain permanent even when a key is requested explicitly.
+
+## What it computes
+
+- Aggregate nodes for exact `(operation_type, component)` categories and weighted directed
+  transitions between adjacent steps.
+- Complete exact paths with stable SHA-256 identities and frequency/outcome summaries.
+- Adjacent exact-category retries and non-adjacent return loops, reported separately.
+- Reconciled success, failure, handoff, drop-off, and unknown outcomes.
+- Failure points, drop-off points, entries, terminals, and successful versus non-successful
+  path comparisons.
+- Event-level duration, token, and supplied-cost summaries with explicit missing counts.
+- Optional cohort summaries based on retained metadata.
+- Structured data-quality and privacy warnings without echoing rejected values.
+
+All ordering, IDs, aggregates, JSON, normalized JSONL, HTML, and SVG are deterministic for the
+same accepted input and configuration. Parent links are diagnostics; normalized chronological
+order is authoritative, with `step_id` as the equal-timestamp tie-breaker.
+
+## Supported inputs
+
+| Input | Maturity | Boundary |
+| --- | --- | --- |
+| JSON Lines | Stable canonical v1 | One `journeygraph.event/v1` object per line. |
+| CSV | Stable canonical v1 | Same scalar fields; metadata uses `metadata.<key>` columns. |
+| Parquet | Optional canonical v1 | Same logical columns through `journeygraph[parquet]` and PyArrow. |
+| OTLP/JSON | Experimental | Explicit `--format otlp-json`; one uncompressed OTLP/HTTP `ExportTraceServiceRequest` JSON body. |
+
+The experimental importer verifies an official OTLP request shape and maps a documented
+subset of OpenTelemetry and OpenInference attributes. It is not a collector, live receiver,
+gRPC or protobuf-binary decoder, generic JSON importer, or claim of Langfuse/Phoenix/provider
+compatibility. Validate a representative sanitized export before relying on it. See the exact
+[data schema and mappings](docs/schema.md).
+
+## Where it fits
+
+For AI systems, a journey might be:
+
+```text
+request -> router -> retrieval -> model -> tool -> validation -> outcome
+```
+
+The same canonical model also supports non-AI operational journeys such as service workflows,
+batch pipelines, product events, support escalation, approval processes, or test-run steps.
+JourneyGraph describes observed associations; it does not infer causes or judge quality.
+
+The implementation keeps provider-specific decoding at the ingestion boundary:
+
+```text
+local export -> reader -> validation/privacy normalization -> aggregate graph
+             -> deterministic analytics -> JSON + normalized JSONL + HTML + SVG
+```
+
+The analytical core uses only the Python standard library. Optional PyArrow is isolated to
+Parquet ingestion. See [Architecture](docs/architecture.md) for dependency boundaries and
+stable identity rules.
+
+## Privacy and security boundary
+
+JourneyGraph denies metadata by default except for a small operational allowlist. Keys matching
+the documented sensitive fragments—including prompt, message, document, credential, token,
+email, and common identifier names—are permanently excluded. Reports escape untrusted markup;
+HTML has no executable JavaScript or remote dependency, and SVG has no scripts or remote
+resources.
+
+This is key-based filtering, not content inspection, anonymization, or a DLP system. An
+arbitrary custom key or value can still identify someone even when its name does not match the
+denylist. Retained IDs, timestamps, labels, allowed values, rare paths, and `normalized.jsonl`
+may still be sensitive. Inspect artifacts before sharing them. Read the full [Privacy and
+Threat Model](docs/privacy.md).
+
+## Quality and reproducibility
+
+The repository has three test layers: pure unit tests, real-file integration tests, and
+black-box installed-CLI functional tests. The acceptance suite covers deterministic ordering,
+branches, retries, loops, outcomes, malformed data, duplicates, privacy leakage, hostile
+markup, Unicode, output safety, canonical formats, representative OTLP/JSON, and a real
+Parquet file when the optional dependency is installed.
+
+The canonical local gate enforces Ruff formatting/linting, strict mypy, combined statement and
+branch coverage of at least 90%, an isolated wheel smoke test, documentation contracts,
+dependency auditing, Bandit, and secret scanning:
+
+```bash
+make setup
+make verify
+```
+
+Mutation testing and the deterministic 2,000-trace benchmark are explicit additional checks:
+
+```bash
+make mutation
+make benchmark
+```
+
+CI runs the same Make targets on Linux with Python 3.11, 3.12, 3.13, and 3.14. A separate
+native Windows job on Python 3.12 builds the distributions, installs the exact wheel in an
+isolated environment, and exercises CLI help, CRLF/Unicode validation, deterministic analysis,
+and the packaged demo. No remote CI result is claimed until that workflow actually runs. See
+[Testing and Quality](docs/testing.md).
+
+## Current limitations and non-goals
+
+- Batch, local, in-memory analysis only; no collection, streaming, server, hosted service, or
+  graph database.
+- Exact category and path grouping only; no fuzzy clustering, causal inference, prediction,
+  anomaly truth, or LLM-as-a-judge.
+- OTLP/JSON support is intentionally narrower than the complete protocol and semantic
+  convention surface.
+- Supplied token and cost values are summarized as-is; provider pricing is not recalculated.
+- Whole multi-file publication is not transactional, although each artifact uses guarded
+  sibling replacement.
+- The installed package and CLI are tested natively on Windows with Python 3.12. Repository
+  development commands still use the documented POSIX Makefile harness or WSL.
+
+## Roadmap
+
+Near-term work should be driven by sanitized real-export evidence: harden canonical and OTLP
+adapters, improve large-input behavior, add explainable comparisons and filtering, and expand
+visual navigation without weakening static/local guarantees. Leakage-safe prefix prediction
+is a possible later experiment only after temporal evaluation and privacy safeguards exist; it
+is not part of 0.1.
+
+## Documentation
+
+- [CLI and Python API](docs/cli.md)
+- [Data and Analysis Schemas](docs/schema.md)
+- [Architecture](docs/architecture.md)
+- [Privacy and Threat Model](docs/privacy.md)
+- [Privacy-safe real-trace discovery](docs/real-trace-discovery.md)
+- [Testing and Quality](docs/testing.md)
+- [Product brief](docs/product-brief.md)
+- [MVP execution plan](docs/exec-plans/journeygraph-mvp.md)
+- [Real-trace discovery execution plan](docs/exec-plans/real-trace-discovery.md)
+- [PyPI Trusted Publishing preparation](docs/exec-plans/pypi-trusted-publishing.md)
+- [Release process](docs/releasing.md)
+
+The experimental standards boundary is anchored to the [OTLP
+specification](https://opentelemetry.io/docs/specs/otlp/), pinned [OpenTelemetry protobuf
+v1.10.0](https://github.com/open-telemetry/opentelemetry-proto/tree/v1.10.0), and
+[OpenInference semantic conventions](https://arize-ai.github.io/openinference/spec/semantic_conventions.html).
+
+## Contributing
+
+Issues and small, evidence-backed changes are welcome. Significant changes to schema meaning,
+privacy, stable identities, format compatibility, or architecture need an approved ExecPlan.
+Please read [CONTRIBUTING.md](CONTRIBUTING.md), the [Code of Conduct](CODE_OF_CONDUCT.md), and
+the [Security Policy](SECURITY.md) before submitting material.
+
+## License
+
+JourneyGraph is available under the [Apache License 2.0](LICENSE).