Graph-Native Infrastructure for Context and Accountable AI Systems
Python agent-memoryaiai-governanceai-infrastructureartificial-intelligencecontext-engineeringcontext-graphsdata-engineeringdecision-intelligencedeveloper-toolsexplainable-aigenerative-aigraph-ragknowledge-graphllmontologyprovenancepythonreasoningsemantic-search
fix: prevent fallback recursion and write proper Parquet in embed generate command
Varun Sahnid42af280e857
diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.ymldeleted file mode 100644index 0157ee24..00000000--- a/.github/workflows/benchmark.yml+++ /dev/null@@ -1,51 +0,0 @@-name: Semantica Performance Suite--on:- workflow_dispatch:--permissions:- contents: read--jobs:- performance-test:- name: Benchmark Runner (Ubuntu/Python 3.12)- runs-on: ubuntu-latest-- steps:- - name: Checkout Code- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- with:- fetch-depth: 0-- - name: Set up Python 3.11- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: "3.11"- cache: 'pip'-- - name: Install Dependencies- env:-- BENCHMARK_REAL_LIBS: "1"- run: |- python -m pip install --upgrade pip- pip install -e .- pip install -r benchmarks/requirements.txt- python -m spacy download en_core_web_sm- pip install rdflib neo4j faiss-cpu torch pyarrow pdfplumber python-pptx openpyxl lxml python-docx beautifulsoup4 chardet langdetect-- - name: Execute Benchmarks (Real Mode)- env:- BENCHMARK_REAL_LIBS: "1"- run: |- python benchmarks/benchmarks_runner.py- # Optional: Compare to baseline (requires previous run artifact)- # pytest-benchmark --storage file://benchmarks/results --benchmark-compare-- - name: Upload Benchmark Results- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7- if: always()- with:- name: benchmark-report-${{ github.run_id }}- path: benchmarks/results- retention-days: 30diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.ymldeleted file mode 100644index 4ea31ff8..00000000--- a/.github/workflows/ci.yml+++ /dev/null@@ -1,83 +0,0 @@-name: CI--permissions:- contents: read--on:- push:- branches: [main]- paths-ignore:- - 'docs/**'- - 'docs_check.py'- - '**/*.md'- pull_request:- branches: [main]- paths-ignore:- - 'docs/**'- - 'docs_check.py'- - '**/*.md'--jobs:- build:- runs-on: ubuntu-latest- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: '3.11'- - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7- with:- node-version: '20'- cache: 'npm'- cache-dependency-path: explorer/package-lock.json- - name: Install Explorer frontend dependencies- working-directory: explorer- run: npm ci- - name: Test Explorer frontend- working-directory: explorer- run: |- npm run test:graph-store- npm run test:graph-workspace- npm run test:plugin-registry- - name: Build Explorer frontend- working-directory: explorer- run: npm run build- - name: Install pinned Python dependencies- run: |- pip install -r requirements-ci.txt- - name: Verify requirements-ci.txt is up to date- run: |- pip install uv==0.12.1- # Re-resolve with the committed file as a constraint: upstream package- # releases must NOT fail CI (deps only change when pyproject.toml- # changes intentionally). Compare only version lines (pkg==ver),- # ignoring the -c constraint comments and the `\` line continuations- # that --generate-hashes emits.- uv pip compile pyproject.toml --python-version 3.11 --extra all \- --constraint requirements-ci.txt -o /tmp/requirements-ci-check.txt- diff \- <(grep -E '^[a-zA-Z0-9._-]+==' requirements-ci.txt | sed 's/ \\$//') \- <(grep -E '^[a-zA-Z0-9._-]+==' /tmp/requirements-ci-check.txt)- - run: pip install build- # wheel is build-time only (not in requirements-ci.txt) — install the- # same pinned version [build-system] declares so --no-isolation works.- - run: pip install wheel==0.48.0- - name: Build package (no isolation — pinned deps)- run: python -m build --no-isolation- - name: Verify Explorer frontend is packaged- run: |- python - <<'PY'- import zipfile- from pathlib import Path-- wheels = list(Path("dist").glob("*.whl"))- assert wheels, "No wheel was built"-- with zipfile.ZipFile(wheels[0]) as wheel:- names = set(wheel.namelist())-- assert "semantica/static/index.html" in names, "Explorer index.html missing from wheel"- assert any(name.startswith("semantica/static/assets/") for name in names), "Explorer assets missing from wheel"-- print("Explorer frontend is packaged")- PYdiff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.ymldeleted file mode 100644index 0c15e84c..00000000--- a/.github/workflows/codeql.yml+++ /dev/null@@ -1,97 +0,0 @@-name: CodeQL--on:- push:- branches: [main]- pull_request:- branches: [main]- schedule:- - cron: '30 1 * * 1' # Every Monday 7 AM IST--permissions:- contents: read- security-events: write- actions: read--jobs:- analyze:- name: Analyze Python- runs-on: ubuntu-latest-- steps:- - name: Checkout repository- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7-- # The CodeQL bundle download (github/codeql-action/init's "Setup CodeQL- # tools" step) streams a ~1GB tarball from GitHub's release CDN and- # does not retry on a transient connection reset (ECONNRESET) itself- # (github/codeql-action, unresolved as of v4 / CLI 2.26.1: the HTTP- # error is retryable but isn't retried internally). Since a `uses:`- # step can't be wrapped by a shell-level retry action, attempt init- # up to 3 times; each retry is a fresh download attempt with no- # meaningful state carried over from a failed attempt.- - name: Initialize CodeQL (attempt 1)- id: codeql-init-1- uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- continue-on-error: true- with:- languages: python- queries: security-and-quality- config-file: .github/codeql/codeql-config.yml-- - name: Initialize CodeQL (attempt 2)- id: codeql-init-2- if: steps.codeql-init-1.outcome == 'failure'- uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- continue-on-error: true- with:- languages: python- queries: security-and-quality- config-file: .github/codeql/codeql-config.yml-- - name: Initialize CodeQL (attempt 3)- id: codeql-init-3- if: steps.codeql-init-2.outcome == 'failure'- uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- with:- languages: python- queries: security-and-quality- config-file: .github/codeql/codeql-config.yml-- - name: Autobuild- uses: github/codeql-action/autobuild@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4-- - name: Perform CodeQL Analysis- uses: github/codeql-action/analyze@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- with:- category: "/language:python"- upload: false- id: codeql-- - name: Upload SARIF (Advanced Setup only)- # Uploads results only when Default Setup is not active.- # If Default Setup is still enabled, this step skips gracefully- # instead of failing the workflow with HTTP 409.- uses: github/codeql-action/upload-sarif@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- with:- sarif_file: ${{ steps.codeql.outputs.sarif-output }}- category: "/language:python"- wait-for-processing: true- continue-on-error: true-- # NOTE: Auto-dismissal by rule-id is intentionally removed.- # Dismissing every alert that matches a rule ID would silently suppress- # future real vulnerabilities of the same type. The alerts below were- # individually triaged and dismissed manually in the security-enhancement- # PR (alerts #12–#18). New alerts must be reviewed and dismissed by hand,- # or will auto-close when the underlying code no longer triggers them.- #- # If you need to dismiss a specific known-safe alert, pin its alert NUMBER- # here and remove it once CodeQL stops reporting it naturally. Example:- #- # PINNED_ALERT_NUMBERS=(12 13 14 15 16 17 18)- # for NUM in "${PINNED_ALERT_NUMBERS[@]}"; do- # gh api repos/$REPO/code-scanning/alerts/$NUM \- # -X PATCH -f state=dismissed -f dismissed_reason="false positive" \- # -f dismissed_comment="<reason>"- # donediff --git a/.github/workflows/defender-for-devops.yml b/.github/workflows/defender-for-devops.ymldeleted file mode 100644index becb7d64..00000000--- a/.github/workflows/defender-for-devops.yml+++ /dev/null@@ -1,88 +0,0 @@-# This workflow uses actions that are not certified by GitHub.-# They are provided by a third-party and are governed by-# separate terms of service, privacy policy, and support-# documentation.-#-# Microsoft Security DevOps (MSDO) is a command line application which integrates static analysis tools into the development cycle.-# MSDO installs, configures and runs the latest versions of static analysis tools-# (including, but not limited to, SDL/security and compliance tools).-#-# The Microsoft Security DevOps action is currently in beta and runs on the windows-latest queue,-# as well as Windows self hosted agents. ubuntu-latest support coming soon.-#-# For more information about the action , check out https://github.com/microsoft/security-devops-action-#-# Please note this workflow do not integrate your GitHub Org with Microsoft Defender For DevOps. You have to create an integration-# and provide permission before this can report data back to azure.-# Read the official documentation here : https://learn.microsoft.com/en-us/azure/defender-for-cloud/quickstart-onboard-github--name: "Microsoft Defender For Devops"--on:- push:- branches: [ "main" ]- pull_request:- branches: [ "main" ]- schedule:- - cron: '43 17 * * 6'--permissions:- contents: read- security-events: write--jobs:- MSDO:- # currently only windows-latest is supported- runs-on: windows-latest-- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - uses: actions/setup-dotnet@a98b56852c35b8e3190ac28c8c2271da59106c68 # v6- with:- dotnet-version: |- 5.0.x- 6.0.x- - name: Run Microsoft Security DevOps- uses: microsoft/security-devops-action@08976cb623803b1b36d7112d4ff9f59eae704de0 # v1.12.0- id: msdo- with:- # checkov is intentionally excluded from this MSDO step.- # MSDO 0.215.0's guardian.cmd wrapper treats checkov's exit code 1- # (emitted whenever any violation is found, even below the active severity- # threshold) as a fatal "tool error" and breaks the build even when- # "Active results: 0" and "Found no breaking results." The .checkov.yaml- # soft-fail setting is never read by the guardian wrapper.- # IaC security scanning continues below in this same MSDO job identity.- # That preserves the existing GitHub code-scanning configuration while- # avoiding the guardian.cmd/checkov exit-code bug in the MSDO wrapper.- tools: eslint,templateanalyzer,terrascan- - name: Upload results to Security tab- uses: github/codeql-action/upload-sarif@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- with:- sarif_file: ${{ steps.msdo.outputs.sarifFile }}-- - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: "3.12"-- - name: Install Checkov- run: python -m pip install checkov==3.3.1-- - name: Run Checkov- shell: pwsh- env:- PYTHONUTF8: "1"- run: |- New-Item -ItemType Directory -Force reports | Out-Null- checkov --directory . --framework kubernetes helm dockerfile github_actions secrets bicep arm --soft-fail --output sarif --output-file-path reports/checkov.sarif- if (-not (Test-Path reports/checkov.sarif)) {- $sarif = Get-ChildItem -Path reports -Recurse -Filter *.sarif | Select-Object -First 1- if ($null -eq $sarif) { throw "Checkov did not produce a SARIF file" }- Copy-Item $sarif.FullName reports/checkov.sarif- }-- - name: Upload Checkov results to Security tab- uses: github/codeql-action/upload-sarif@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4- if: always()- with:- sarif_file: reports/checkov.sarifdiff --git a/.github/workflows/docs.yml b/.github/workflows/docs.ymldeleted file mode 100644index ca149d7e..00000000--- a/.github/workflows/docs.yml+++ /dev/null@@ -1,68 +0,0 @@-name: Build and Deploy Documentation--on:- push:- branches: [main]- paths:- - 'docs/**'- - 'docs_check.py'- - 'CHANGELOG.md'- - 'RELEASE.md'- pull_request:- branches: [main]- paths:- - 'docs/**'- - 'docs_check.py'- workflow_dispatch:--permissions:- contents: read- pages: write- id-token: write--concurrency:- group: "pages"- cancel-in-progress: false--jobs:- validate:- name: Validate Documentation- runs-on: ubuntu-latest- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: '3.11'- - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7- with:- node-version: '20'- - run: python docs_check.py-- deploy:- name: Build and Deploy to GitHub Pages- if: github.event_name != 'pull_request'- runs-on: ubuntu-latest- needs: validate- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7-- - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7- with:- node-version: '20'-- - name: Export static site- run: |- cd docs- npx mintlify export --output ../export.zip- cd ..- unzip -q export.zip -d site-- - uses: actions/configure-pages@45bfe0192ca1faeb007ade9deae92b16b8254a0d # v6-- - uses: actions/upload-pages-artifact@fc324d3547104276b827a68afc52ff2a11cc49c9 # v5- with:- path: ./site-- - name: Deploy to GitHub Pages- id: deployment- uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymldeleted file mode 100644index bbc8770c..00000000--- a/.github/workflows/release.yml+++ /dev/null@@ -1,73 +0,0 @@-name: Release--on:- push:- tags: ['v*']--permissions:- contents: read--jobs:- release:- runs-on: ubuntu-latest- environment: pypi- concurrency:- group: release-${{ github.ref }}- cancel-in-progress: false- permissions:- contents: write # for the GitHub Release- id-token: write # for PyPI Trusted Publishing (OIDC) and attestation signing- attestations: write # for SLSA build provenance- # If you add another job to this workflow, give it its own explicit- # `permissions:` block rather than relying on the workflow-level default- # above (contents: read) - do not widen the workflow-level default.- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: '3.11'- - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7- with:- node-version: '20'- cache: 'npm'- cache-dependency-path: explorer/package-lock.json- - name: Build Explorer frontend- working-directory: explorer- run: |- npm ci- npm run build- # Install the pinned dependency set (with hashes) so the sdist/wheel- # build runs against the same versions CI tests against.- - name: Install pinned build dependencies- run: pip install -r requirements-ci.txt- - run: pip install build- # wheel is build-time only (not in requirements-ci.txt) — install the- # same pinned version [build-system] declares so --no-isolation works.- - run: pip install wheel==0.48.0- - name: Build package (no isolation — pinned deps)- run: python -m build --no-isolation- - name: Verify Explorer frontend is packaged- run: |- python - <<'PY'- import zipfile- from pathlib import Path-- wheels = list(Path("dist").glob("*.whl"))- assert wheels, "No wheel was built"-- with zipfile.ZipFile(wheels[0]) as wheel:- names = set(wheel.namelist())-- assert "semantica/static/index.html" in names, "Explorer index.html missing from wheel"- assert any(name.startswith("semantica/static/assets/") for name in names), "Explorer assets missing from wheel"-- print("Explorer frontend is packaged")- PY- - name: Attest build provenance- uses: actions/attest-build-provenance@4d101475d8b20a2381f78447822ac1eab6504dd8 # v4- with:- subject-path: 'dist/*'- - uses: softprops/action-gh-release@3d0d9888cb7fd7b750713d6e236d1fcb99157228 # v3- with:- files: dist/*- - uses: pypa/gh-action-pypi-publish@dc37677b2e1c63e2034f94d8a5b11f265b73ba33 # release/v1diff --git a/.github/workflows/security-scan.yml b/.github/workflows/security-scan.ymldeleted file mode 100644index 5b4461af..00000000--- a/.github/workflows/security-scan.yml+++ /dev/null@@ -1,239 +0,0 @@-name: Security Scan--on:- schedule:- - cron: '30 1 * * 1,4' # Mon/Thu 7 AM IST- push:- branches: [main]- paths-ignore:- - 'docs/**'- - 'mkdocs.yml'- - 'requirements-docs.txt'- - '**/*.md'- pull_request:- branches: [main]- paths-ignore:- - 'docs/**'- - 'mkdocs.yml'- - 'requirements-docs.txt'- - '**/*.md'--permissions:- contents: read--jobs:- security-scan:- runs-on: ubuntu-latest- permissions:- contents: read- security-events: write- actions: read- # Needed for the "Comment PR with Security Results" step below. Safe on- # pull_request (not pull_request_target): GitHub always forces a- # read-only token for PRs from forks regardless of this permission.- pull-requests: write-- steps:- - name: Checkout repository- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7-- - name: Set up Python- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: '3.11'-- - name: Install dependencies- run: |- python -m pip install --upgrade pip- # Install the pinned dependency set FIRST so Safety scans Semantica's- # exact CI/release dependency tree (requirements-ci.txt is generated- # from pyproject.toml extras, so this covers the project's real deps).- pip install -r requirements-ci.txt- # Tooling AFTER the pinned set: installing safety/bandit/semgrep/jq- # first lets the pinned requirements overwrite their transitive deps- # (e.g. rich), which breaks the safety CLI at runtime.- pip install safety bandit semgrep jq-- - name: Run Safety Check (Package Vulnerabilities)- run: |- # NOTE: Safety 3.x repurposed --output to select a console format- # (json/text/screen/...), not a file path. Writing JSON to a file- # now requires --save-json; the previous `--output safety-report.json`- # usage was silently invalid and never produced a report.- safety check --save-json safety-report.json || true-- # Guard 1: fail loudly if Safety exited before writing a report at all- # (network error, API auth failure, tool crash). Without this check a- # missing or empty file causes jq to fall back to "0", making a broken- # scanner indistinguishable from a clean scan.- if [ ! -s safety-report.json ]; then- echo "::error::Safety scan produced no report (safety-report.json is missing or empty). Treating as failure — check for network errors, API auth failures, or Safety crashes in the logs above."- exit 1- fi-- echo "Checking for package vulnerabilities..."-- # No || echo "0" fallback: if jq fails (malformed JSON, missing key,- # vulnerabilities:null) VULNS will be empty or "null" so guard 2 below- # catches it rather than silently treating the broken report as zero.- VULNS=$(jq '.vulnerabilities | length' safety-report.json 2>/dev/null)-- # Guard 2: ensure VULNS is a non-negative integer before the -gt- # comparison. "null" (missing/null key) or "" (jq parse failure) would- # cause bash's -gt to throw an arithmetic error and fall through to the- # success branch — the same silent-pass bug as a missing file.- if ! [[ "$VULNS" =~ ^[0-9]+$ ]]; then- echo "::error::Safety report exists but 'vulnerabilities' is missing or non-numeric (got: '${VULNS}'). The report may be malformed or Safety may have written an error-only JSON. Treating as failure."- exit 1- fi-- if [ "$VULNS" -gt 0 ]; then- echo "❌ Security vulnerabilities found: $VULNS"- echo "CI will fail to prevent merging of vulnerable dependencies"- echo ""- echo "Vulnerability details:"- jq -r '.vulnerabilities[] | "- \(.package_name)==\(.analyzed_version): \(.vulnerability_id) (\(.CVE // "no CVE assigned"))"' safety-report.json || true- exit 1- else- echo "✅ No security vulnerabilities found"- fi-- - name: Run Bandit (Code Security Linter)- run: |- bandit -r semantica/ -f json -o bandit-report.json || true- echo "Checking for HIGH severity security issues..."-- # Count HIGH severity issues- HIGH_ISSUES=$(bandit -r semantica/ -f json -ll 2>/dev/null | jq -r '.results[]? | select(.issue_severity == "HIGH") | .test_name' 2>/dev/null | wc -l || echo "0")-- if [ "$HIGH_ISSUES" -gt 0 ]; then- echo "❌ HIGH severity security issues found: $HIGH_ISSUES"- echo "CI will fail to prevent merging of high-risk code"- echo ""- echo "High severity issues:"- bandit -r semantica/ -ll | grep "Severity: High" -A 5 -B 1 || true- exit 1- else- echo "✅ No HIGH severity security issues found"- fi-- - name: Run Semgrep (Static Analysis)- run: |- echo "Running Semgrep static analysis..."- semgrep --config=auto --json --output=semgrep-report.json semantica/ || true-- # Run security-focused rules- echo "Checking for security patterns..."- SECURITY_ISSUES=$(semgrep --config=p/security --json semantica/ 2>/dev/null | jq '.results | length' 2>/dev/null || echo "0")-- if [ "$SECURITY_ISSUES" -gt 0 ]; then- echo "⚠️ Security patterns found: $SECURITY_ISSUES"- echo "Review these findings for potential improvements"- semgrep --config=p/security semantica/ || true- else- echo "✅ No security patterns found"- fi-- - name: Upload Security Reports- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7- with:- name: security-reports- retention-days: 14- path: |- safety-report.json- bandit-report.json- semgrep-report.json-- - name: Comment PR with Security Results- if: github.event_name == 'pull_request'- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9- with:- script: |- const fs = require('fs');-- // Renders one tool's findings as a section. `items` is already- // the list of pre-formatted "- `thing` in `where`" strings; this- // just handles the found/not-found/report-missing framing and- // collapses long lists into a <details> block so the comment- // doesn't turn into a wall of text.- function renderSection(title, reportPath, parse) {- let data;- try {- data = JSON.parse(fs.readFileSync(reportPath, 'utf8'));- } catch (e) {- return [- `### ${title}`,- `⚠️ No report found at \`${reportPath}\` — the scan may have failed before producing output. Check the job logs.`,- ].join('\n');- }-- const items = parse(data);- if (items.length === 0) {- return [`### ${title}`, `✅ No findings.`].join('\n');- }-- const lines = [`### ${title}`, `Found **${items.length}**.`, ''];- const shown = items.slice(0, 15);- if (items.length > 15) {- lines.push('<details>', '<summary>Show all findings</summary>', '');- lines.push(...items);- lines.push('', '</details>');- } else {- lines.push(...shown);- }- return lines.join('\n');- }-- const safetySection = renderSection(- 'Safety — dependency vulnerabilities',- 'safety-report.json',- (data) => (data.vulnerabilities || []).map(- (v) => `- \`${v.package_name}==${v.analyzed_version}\`: ${v.vulnerability_id}` +- (v.CVE ? ` (${v.CVE})` : '') + ` — ${v.advisory || 'no advisory text'}`- )- );-- const banditSection = renderSection(- 'Bandit — HIGH-severity code issues',- 'bandit-report.json',- (data) => (data.results || [])- .filter((issue) => issue.issue_severity === 'HIGH')- .map((issue) => `- \`${issue.test_name}\` in \`${issue.filename}:${issue.line_number}\``)- );-- const semgrepSection = renderSection(- 'Semgrep — static analysis patterns',- 'semgrep-report.json',- (data) => (data.results || []).map(- (issue) => `- \`${issue.check_id}\` in \`${issue.path}:${issue.start?.line ?? '?'}\``- )- );-- const comment = [- '# 🔒 Security Scan Results',- '',- safetySection,- '',- banditSection,- '',- semgrepSection,- '',- '---',- '',- '*This security scan runs automatically on source-code PRs and bi-weekly (skipped for doc/markdown-only changes).*',- '',- '📊 **Security Policy**: CI fails on Safety vulnerabilities and Bandit HIGH-severity findings. Semgrep findings above are informational and do not block merge.',- ].join('\n');-- try {- await github.rest.issues.createComment({- issue_number: context.issue.number,- owner: context.repo.owner,- repo: context.repo.repo,- body: comment,- });- console.log('✅ Security comment posted successfully');- } catch (error) {- console.log('⚠️ Could not post security comment:', error.message);- console.log('📋 Security scan results saved to artifacts');- }diff --git a/.github/workflows/security.yml b/.github/workflows/security.ymldeleted file mode 100644index 412e7eaa..00000000--- a/.github/workflows/security.yml+++ /dev/null@@ -1,42 +0,0 @@-name: Security--on:- schedule:- - cron: '0 0 * * 1'- workflow_dispatch:- pull_request:- branches: [main]- paths:- - 'pyproject.toml'- - 'requirements-ci.txt'- - '.github/workflows/security.yml'--permissions:- contents: read--jobs:- audit:- runs-on: ubuntu-latest- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7- with:- python-version: '3.11'- # Upgrade first: actions/setup-python's baked-in setuptools has been- # behind known-vulnerable floors before (e.g. PYSEC-2026-3447 /- # setuptools 75.1.0), so don't trust the preinstalled one.- - run: python -m pip install --upgrade pip setuptools- # Audit the pinned dependency set (requirements-ci.txt is compiled from- # pyproject.toml with --extra all — the same coverage as the [all]- # extra, minus the Linux-only gpu set — so this keeps scan parity with- # CI/release builds without a time-dependent resolution). This is the- # fix for PYSEC-2024-38 (#869): the bare-env job never had fastapi or- # python-multipart installed to look at.- - run: pip install -r requirements-ci.txt- # PR runs gate on findings, since they're scoped to actual- # pyproject.toml changes under review. The schedule/workflow_dispatch- # runs stay non-blocking until a full pass over pre-existing findings- # across the whole [all] tree has been done.- - run: pip install pip-audit- - run: pip-audit -r requirements-ci.txt- continue-on-error: ${{ github.event_name != 'pull_request' }}diff --git a/.github/workflows/verify-action-pins.yml b/.github/workflows/verify-action-pins.ymldeleted file mode 100644index 6e7dada9..00000000--- a/.github/workflows/verify-action-pins.yml+++ /dev/null@@ -1,28 +0,0 @@-name: Verify Action Pins--on:- pull_request:- paths:- - '.github/workflows/**'- - '.github/scripts/verify-action-pins.sh'- push:- branches: [main]- paths:- - '.github/workflows/**'- - '.github/scripts/verify-action-pins.sh'- schedule:- - cron: '0 3 * * 1' # weekly, in case an upstream tag is deliberately moved- workflow_dispatch:--permissions:- contents: read--jobs:- verify:- runs-on: ubuntu-latest- steps:- - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7- - name: Verify pinned action SHAs match their tag comments- env:- GH_TOKEN: ${{ github.token }}- run: bash .github/scripts/verify-action-pins.shdiff --git a/pyproject.toml b/pyproject.tomlindex 03949d4e..738e68ef 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -85,7 +85,8 @@ dependencies = ["loguru>=0.7.3","structlog>=22.1.0","gensim>=4.4.0",- "httpx<0.29.0"+ "httpx<0.29.0",+ "pyarrow>=14.0.0"][project.urls]diff --git a/semantica/cli.py b/semantica/cli.pyindex 7b944dc6..b5e14ebd 100644--- a/semantica/cli.py+++ b/semantica/cli.py@@ -1708,7 +1708,28 @@ def embed_generate(cli_ctx: CLIContext, input_path: str, model: str,except ImportError as exc:raise click.ClickException(f"Embeddings module not available: {exc}") from excif output:- Path(output).write_text(json.dumps(result, default=str), encoding="utf-8")+ output_path = Path(output)+ try:+ import numpy as np+ import pandas as pd+ if output_path.suffix.lower() == ".parquet":+ arr = np.asarray(result)+ if arr.ndim == 1:+ arr = arr[np.newaxis, :]+ # schema: one column per embedding plus an id column+ columns = [f"dim_{i}" for i in range(arr.shape[1])]+ df = pd.DataFrame(arr, columns=columns)+ df.index.name = "id"+ df.to_parquet(output_path, index=True)+ else:+ output_path.write_text(+ json.dumps(result, default=str), encoding="utf-8"+ )+ except ImportError as exc:+ raise click.ClickException(+ f"Missing dependency for --output: {exc}. "+ f"Install pyarrow/pandas with: pip install semantica[ingest-parquet]"+ ) from exc_ok(cli_ctx, f"Wrote {output}")elif _is_json(cli_ctx, local_json):_jecho(result if isinstance(result, dict) else {"status": "ok"})diff --git a/semantica/embeddings/methods.py b/semantica/embeddings/methods.pyindex 30c47279..d2e8848e 100644--- a/semantica/embeddings/methods.py+++ b/semantica/embeddings/methods.py@@ -116,9 +116,9 @@ def generate_embeddings(>>> emb = generate_embeddings("Hello world", method="default")>>> embs = generate_embeddings(["text1", "text2"], method="text")"""- # Check for custom method in registry+ # Check for custom method in registry, skip self-referencecustom_method = method_registry.get("generation", method)- if custom_method:+ if custom_method and custom_method is not generate_embeddings:try:return custom_method(data, data_type=data_type, **kwargs)except Exception as e:@@ -164,9 +164,9 @@ def embed_text(>>> emb = embed_text("Hello world", method="sentence_transformers")>>> embs = embed_text(["text1", "text2"], method="sentence_transformers")"""- # Check for custom method in registry+ # Check for custom method in registry, skip self-referencecustom_method = method_registry.get("text", method)- if custom_method:+ if custom_method and custom_method is not embed_text:try:return custom_method(text, **kwargs)except Exception as e:@@ -224,9 +224,9 @@ def calculate_similarity(>>> similarity = calculate_similarity(emb1, emb2, method="cosine")>>> print(f"Similarity: {similarity:.3f}")"""- # Check for custom method in registry+ # Check for custom method in registry, skip self-referencecustom_method = method_registry.get("similarity", method)- if custom_method:+ if custom_method and custom_method is not calculate_similarity:try:return custom_method(embedding1, embedding2, **kwargs)except Exception as e:@@ -271,9 +271,9 @@ def pool_embeddings(>>> pooled = pool_embeddings(embeddings, method="mean")>>> attention_pooled = pool_embeddings(embeddings, method="attention")"""- # Check for custom method in registry+ # Check for custom method in registry, skip self-referencecustom_method = method_registry.get("pooling", method)- if custom_method:+ if custom_method and custom_method is not pool_embeddings:try:return custom_method(embeddings, **kwargs)except Exception as e: