pytagmanager 0.2.0__tar.gz → 0.2.2__tar.gz

pytagmanager-0.2.2/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,65 @@
+name: Bug report
+description: Report something that's broken or not working as documented
+labels: ["bug"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Before filing: check `ROADMAP_HONEST.md` first — the behavior you're
+        seeing might be a documented, known gap rather than an undiscovered bug.
+
+  - type: input
+    id: version
+    attributes:
+      label: PyTagManager version
+      description: Output of `pip show pytagmanager` or the git commit you're on
+      placeholder: "0.2.0, or commit sha"
+    validations:
+      required: true
+
+  - type: input
+    id: python-version
+    attributes:
+      label: Python version
+      placeholder: "3.9 / 3.11 / ..."
+    validations:
+      required: true
+
+  - type: input
+    id: os
+    attributes:
+      label: Operating system
+      placeholder: "macOS 14, Ubuntu 22.04, ..."
+    validations:
+      required: true
+
+  - type: textarea
+    id: command
+    attributes:
+      label: Command run
+      description: The exact `pytagmanager ...` command (or Python snippet) that triggered the bug
+      render: shell
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual behavior
+      description: Include the full error/traceback if there is one
+      render: shell
+    validations:
+      required: true
+
+  - type: textarea
+    id: extras
+    attributes:
+      label: Was the `diagnostics` extra installed? Was Playwright's Chromium installed?
+      placeholder: "pip install 'pytagmanager[diagnostics]' && playwright install chromium"

pytagmanager-0.2.2/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,46 @@
+name: Feature request
+description: Propose a new capability or improvement
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Before filing: check `docs/VISION.md` and `docs/ROADMAP.md` — your
+        idea may already be a planned (or deliberately deferred, with a
+        stated reason) phase. If so, comment on that context instead of
+        opening a duplicate.
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: What problem does this solve?
+      description: Describe the gap or friction you're hitting today, not just the feature itself
+    validations:
+      required: true
+
+  - type: textarea
+    id: proposal
+    attributes:
+      label: Proposed solution
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives considered
+      description: Including any existing PyTagManager flag/feature that gets partway there
+
+  - type: dropdown
+    id: north-star
+    attributes:
+      label: Which of the five north-star questions (docs/VISION.md) does this serve?
+      options:
+        - "What data exists?"
+        - "Where does it exist?"
+        - "When does it exist?"
+        - "Is it usable by the tagging layer?"
+        - "What is missing or broken?"
+        - "Not sure / none of these"
+    validations:
+      required: false

pytagmanager-0.2.2/.github/dependabot.yml

@@ -0,0 +1,19 @@
+version: 2
+updates:
+  - package-ecosystem: "cargo"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 10
+
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 10
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 5

pytagmanager-0.2.2/.github/pull_request_template.md

@@ -0,0 +1,21 @@
+## What changed and why
+
+<!-- Link the roadmap phase (docs/ROADMAP.md) or issue this relates to, if any. -->
+
+## Testing
+
+<!-- What did you actually run? Paste real command + output/pass-fail, not "tests pass". -->
+
+- [ ] `cargo fmt --check` / `cargo clippy --all-targets -- -D warnings` (Rust changes only)
+- [ ] `cargo test` (Rust changes only)
+- [ ] `pytest tests/python -v` (Python changes only — note if you ran the full suite or a subset)
+
+## Documentation
+
+- [ ] Updated `README.md` / `ROADMAP_HONEST.md` / `docs/` if this changes what's built, tested, or working
+- [ ] Did not describe untested code as working, and did not soften a known limitation (see `CONTRIBUTING.md`'s documentation honesty policy)
+
+## Checklist
+
+- [ ] No secrets/credentials committed
+- [ ] No new `TODO`/`FIXME` left without an issue reference or explicit scope note

{pytagmanager-0.2.0 → pytagmanager-0.2.2}/.github/workflows/ci.yml

@@ -51,3 +51,34 @@ jobs:
 
       - name: pytest tests/python
         run: pytest tests/python -v
+
+  dependency-audit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo
+        uses: Swatinem/rust-cache@v2
+
+      - name: Install cargo-audit
+        run: cargo install cargo-audit --locked
+
+      - name: cargo audit (Rust dependency vulnerabilities)
+        run: cargo audit
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+
+      - name: Install pip-audit and this project's declared dependencies
+        run: |
+          python -m pip install --upgrade pip pip-audit
+          python -m pip install 'click>=8.0' 'playwright>=1.40' 'pyyaml>=6.0' \
+            'google-api-python-client>=2.100' 'google-auth>=2.23' \
+            'google-auth-oauthlib>=1.1'
+
+      - name: pip-audit (Python dependency vulnerabilities)
+        run: pip-audit --strict

{pytagmanager-0.2.0 → pytagmanager-0.2.2}/.gitignore

@@ -4,6 +4,8 @@ __pycache__/
 *.pyc
 *.egg-info/
 .pytest_cache/
+.ruff_cache/
+.mypy_cache/
 dist/
 *.so
 *.pyd

pytagmanager-0.2.2/CHANGELOG.md

@@ -0,0 +1,122 @@
+# Changelog
+
+All notable changes to this project are documented here. Format loosely
+follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); this
+project does not yet follow semantic versioning strictly (see
+`ROADMAP_HONEST.md` for current version/PyPI status).
+
+Entries below are derived from the actual git history and PyPI publish
+notes, not reconstructed from memory — see `ROADMAP_HONEST.md` for the
+authoritative, continuously-updated built-vs-not-built breakdown; this
+file is a release-oriented complement to it, not a duplicate.
+
+## [Unreleased]
+
+## [0.2.2] - 2026-09-27
+
+### Fixed
+
+- `src/crawler/frontier.rs`: `Frontier::has_capacity()` no longer also checks
+  `seen.len() < max_pages` -- that extra check caused the BFS loop to exit as
+  soon as `seen` (URLs *discovered*, not fetched) reached `max_pages`, even
+  while already-accepted URLs were still sitting unfetched in the queue.
+  Concretely, `crawl(url, max_pages=1)` returned zero pages instead of the
+  seed page it should always return. See `ROADMAP_HONEST.md` for full
+  verification detail and the regression tests added.
+
+## [0.2.1] - 2026-09-22
+
+Everything shipped on `main` since the v0.2.0 version bump (2026-08-31),
+published to PyPI as v0.2.1 on 2026-09-22 — see `ROADMAP_HONEST.md`'s CI/CD
+section for the current PyPI status. Highlights, in shipped order:
+
+- Tracking Observability & Diagnostics: Runtime State Capture (cookies/
+  storage/dataLayer snapshots + diffing), Website Data Dictionary (schema
+  drift, presence-vs-availability labeling, purpose classification),
+  broadened browser-behavior intelligence (scroll-depth interactions,
+  cross-implementation consistency checks, Runtime Event Map, formalized
+  Interaction Trace).
+- GTM Client/Server Execution Intelligence & Tag Execution Graph:
+  static tag/vendor scanning (`scan-tags`), duplicate/conflicting
+  implementation detection, hedged server-side tagging indicators, and
+  the unified Tag Execution Graph (`diagnose --tag-graph`).
+- Playwright Discovery & Test Intelligence: evidence-backed Test
+  Candidates generated from diagnosis/consistency/regression findings,
+  with Playwright draft-script export.
+- Automated Script Impact & Web Performance Intelligence
+  (`pytagmanager perf`): real browser-native performance measurement,
+  script inventory + dependency graph, controlled isolation experiments,
+  tagging-vs-performance join, CPU throttling, and history/regression
+  tracking.
+- Client-rendered crawling (`crawl --render`): rendered-DOM discovery,
+  per-page screenshot capture, analytics sniffing, and bounded
+  interaction simulation for sites whose content only exists after JS
+  runs.
+- `OllamaIntentClassifier` wired directly into `crawl --intent ollama`
+  and the public `pytagmanager` API (previously implemented but not
+  reachable from the CLI).
+- `Cargo.toml` version drift fix (was stuck at 0.1.3 while
+  `pyproject.toml`/`__init__.py` had already moved to 0.2.0).
+- CI fix: `ci.yml` now installs the `pytagmanager[diagnostics]` extra and
+  a Playwright Chromium binary before running `pytest` — previously every
+  push since Tracking Observability landed failed pytest's collection
+  phase outright (`ModuleNotFoundError: No module named 'yaml'`).
+
+### Fixed
+
+- `src/lib.rs`: the `crawl()` pyfunction no longer panics (via PyO3's
+  panic-to-`PanicException` conversion) if `tokio::runtime::Runtime::new()`
+  fails — the failure now propagates as a catchable Python `RuntimeError`
+  through a new `AppError::Internal` variant.
+- `src/crawler/fetcher.rs`: `Fetcher::build()` no longer panics if
+  `reqwest::Client::builder().build()` fails — propagated through the
+  `Result<Self, AppError>` the function already returns, same as its other
+  failure modes.
+- `src/crawler/orchestrator.rs`: corrected a stale doc comment on
+  `crawl_with_fetcher` claiming the real entry point calls `Fetcher::new()`
+  — it actually calls `Fetcher::build(true, ...)` directly.
+
+See `ROADMAP_HONEST.md` for exactly which sub-items of the above are
+fully shipped vs. disclosed-partial, and for known bugs/tech debt, plus
+the now-verified (and currently red) `dependency-audit` CI job results.
+
+## [0.2.0] — version bumped in repo 2026-08-31, published to PyPI 2026-09-14
+
+No git tag exists for this release in this repository as of this writing.
+
+- Relicensed the project from a proprietary license to Apache-2.0.
+- Added Tracking Observability & Diagnostics (real-browser interaction →
+  dataLayer → GTM → GA4 correlation, rule-based root-cause diagnosis) and
+  Site-Wide Tagging QA (cross-page template consistency, health scoring).
+- **PyPI platform coverage note**: this release published only a macOS
+  arm64 wheel + sdist (no Docker/zig available locally for manylinux
+  cross-compilation at publish time), narrower than v0.1.3's release
+  (macOS x86_64 + arm64 + Linux x86_64 + aarch64 + sdist). See
+  `ROADMAP_HONEST.md` for detail.
+
+## [0.1.3] — 2026-08-26
+
+- Added non-GTM exporters (GA4, Segment, Snowplow, Tealium, RudderStack,
+  Adobe Tags).
+- Added crawl-to-crawl diffing (`pytagmanager diff`).
+- Added `OllamaIntentClassifier` (local-LLM business-intent
+  classification via Ollama).
+- Published a proprietary LICENSE for the initial public release (later
+  superseded by the Apache-2.0 relicense in 0.2.0).
+- CI fix: create and activate a virtualenv before `maturin develop`.
+- Added README metadata + `abi3-py39` PyO3 feature for broader wheel
+  compatibility.
+
+## [0.1.1] — 2026-08-12
+
+- Added an SSRF guard to the Rust crawler (blocks loopback and cloud
+  metadata-service addresses).
+- Added the Rust/Python integration test suite and initial CI workflow.
+
+## [0.1.0] — initial commit
+
+- Rust crawler (BFS, sitemap.xml, robots.txt) + semantic DOM graph engine
+  (selectors, ARIA).
+- Rule-based tracking recommendation engine.
+- CLI (`pytagmanager crawl`) + GTM export.
+- Initial product vision and roadmap documents.

pytagmanager-0.2.2/CODE_OF_CONDUCT.md

@@ -0,0 +1,64 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in
+our community a harassment-free experience for everyone, regardless of
+age, body size, visible or invisible disability, ethnicity, sex
+characteristics, gender identity and expression, level of experience,
+education, socio-economic status, nationality, personal appearance, race,
+caste, color, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing for mistakes, and learning
+  from the experience
+- Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior:
+
+- The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political
+  attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+This project is currently maintained by a single person (see
+[`SECURITY.md`](SECURITY.md) for the same disclosure re: response times).
+The maintainer is responsible for clarifying and enforcing standards of
+acceptable behavior and will take appropriate and fair corrective action
+in response to any behavior deemed inappropriate, threatening, offensive,
+or harmful — with no guaranteed response time, since there is no
+dedicated moderation team.
+
+## Scope
+
+This Code of Conduct applies within all community spaces for this project
+(GitHub issues, pull requests, discussions), and applies when an
+individual is officially representing the project in public spaces.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may
+be reported to the maintainer via the contact method in
+[`SECURITY.md`](SECURITY.md). All complaints will be reviewed and
+investigated as promptly as a single maintainer can manage.
+
+## Attribution
+
+This Code of Conduct is adapted from the
+[Contributor Covenant](https://www.contributor-covenant.org), version 2.1,
+available at
+https://www.contributor-covenant.org/version/2/1/code_of_conduct.html.

pytagmanager-0.2.2/CONTRIBUTING.md

@@ -0,0 +1,93 @@
+# Contributing to PyTagManager
+
+## Before you start
+
+Read [`README.md`](README.md) for what's actually built and working, and
+[`docs/VISION.md`](docs/VISION.md) + [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md)
+for where the project is going and why. [`ROADMAP_HONEST.md`](ROADMAP_HONEST.md)
+is the current source of truth on what's shipped vs. not — check it before
+assuming a feature is missing or already exists.
+
+This is a solo-maintained project (see [`SECURITY.md`](SECURITY.md) for
+response-time expectations). There is no dedicated maintainer team, no SLA on
+PR review, and no guarantee a given contribution will be merged.
+
+## Development setup
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install maturin pytest
+maturin develop          # builds the Rust extension, installs pytagmanager editable
+
+# Tracking Observability / Diagnostics / Dictionary / Perf tests need the
+# diagnostics extra + a Chromium binary:
+pip install -e '.[diagnostics]'
+playwright install chromium
+```
+
+macOS note: raw `cargo build`/`cargo test` (outside `maturin`) need the
+linker flags in `.cargo/config.toml` for PyO3 extension-module crates to
+link. `maturin develop`/`maturin build` set these automatically; if you
+invoke `cargo` directly and it fails to link, that's why.
+
+## Running the test suite
+
+```bash
+cargo test               # Rust: crawler, sitemap/robots parsing, DOM/selectors
+pytest tests/python -v   # Python: heuristics, exporters, diffing, observability, etc.
+```
+
+Most of the Python suite drives a real headless Chromium instance (no
+mocked browser behavior) — expect it to be slower than a typical unit-test
+suite, and make sure `playwright install chromium` has been run once.
+
+Before submitting a change to Rust code, also run:
+
+```bash
+cargo fmt --check
+cargo clippy --all-targets -- -D warnings
+```
+
+CI runs all of the above; a PR that fails any of them won't pass CI.
+
+## Making a change
+
+1. Fork the repo and create a branch off `main`.
+2. Make your change with tests. A change with no test coverage for the
+   behavior it adds or fixes will generally not be merged — this project's
+   honesty policy (see below) depends on test coverage actually reflecting
+   what's claimed to work.
+3. Run the full validation above locally before opening a PR.
+4. Open a PR describing what changed and why. Reference the roadmap phase
+   or issue it relates to, if any.
+
+## Documentation honesty policy
+
+This project's docs (`README.md`, `ROADMAP_HONEST.md`, `docs/`) are
+maintained to a specific, deliberately blunt standard: no hedging on
+project status. If something isn't built, the docs say "not built," not
+"planned" or "may be added." If something is untested, the docs say so
+explicitly rather than describing it as working. PRs that add a feature
+should update the relevant doc section to match this standard — don't
+describe a new feature as more complete or more tested than it actually is,
+and don't soften a known limitation to make a PR look more finished.
+
+## Code style
+
+- **Rust**: `cargo fmt` (default settings) + `cargo clippy` clean, no
+  suppressed lints without a comment explaining why.
+- **Python**: no enforced formatter is wired into CI yet (see
+  `ROADMAP_HONEST.md` for other CI gaps); match the existing style in the
+  file you're editing. Type hints are used throughout `python/pytagmanager/`
+  — new code should include them.
+
+## Reporting bugs / requesting features
+
+Use the issue templates under `.github/ISSUE_TEMPLATE/`. For security
+issues, do not open a public issue — see [`SECURITY.md`](SECURITY.md).
+
+## License
+
+By contributing, you agree your contributions are licensed under this
+project's [Apache-2.0 license](LICENSE).

{pytagmanager-0.2.0 → pytagmanager-0.2.2}/Cargo.lock

@@ -908,7 +908,7 @@ dependencies = [
 
 [[package]]
 name = "pytagmanager"
-version = "0.2.0"
+version = "0.2.2"
 dependencies = [
  "futures",
  "pyo3",

{pytagmanager-0.2.0 → pytagmanager-0.2.2}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pytagmanager"
-version = "0.2.0"
+version = "0.2.2"
 edition = "2021"
 description = "Rust core (crawler + semantic DOM graph engine) for PyTagManager"
 license = "Apache-2.0"