ai-kit-python 1.4.2__tar.gz

ai_kit_python-1.4.2/.agents/skills/go-work/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: go-work
+description: Apply project Go rules when changing confirmed Go packages, services, or tests.
+---
+
+# Go work
+
+Read [contribution rules](../../../CONTRIBUTING.md) and optional local `../../../PROJECT_CONTEXT.md`, then [Go rules](../../../ai-kit/stacks/GO.md) and relevant [engineering rules](../../../ai-kit/ENGINEERING.md). Check the actual Go version, module structure and test commands before editing.

ai_kit_python-1.4.2/.agents/skills/laravel-work/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: laravel-work
+description: Apply project Laravel rules when changing confirmed Laravel code, models, resources, or migrations.
+---
+
+# Laravel work
+
+Read [contribution rules](../../../CONTRIBUTING.md) and optional local `../../../PROJECT_CONTEXT.md`, then [Laravel rules](../../../ai-kit/stacks/LARAVEL.md) and relevant [engineering rules](../../../ai-kit/ENGINEERING.md). Confirm the installed versions and existing project contracts before editing. If a project rule conflicts with this starter profile, surface the conflict before applying a destructive or incompatible change.

ai_kit_python-1.4.2/.agents/skills/moodle-work/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: moodle-work
+description: Apply project Moodle rules when changing a confirmed Moodle installation or plugin.
+---
+
+# Moodle work
+
+Read [contribution rules](../../../CONTRIBUTING.md) and optional local `../../../PROJECT_CONTEXT.md`, then [Moodle rules](../../../ai-kit/stacks/MOODLE.md) and relevant [engineering rules](../../../ai-kit/ENGINEERING.md). Confirm Moodle/PHP compatibility and the affected plugin type before editing.

ai_kit_python-1.4.2/.agents/skills/project-continuity/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: project-continuity
+description: Maintain AI-KIT's own context, template boundaries, and installer verification when kit structure or procedures change.
+---
+
+# AI-KIT maintenance continuity
+
+Read [contribution rules](../../../CONTRIBUTING.md). Read optional local `../../../PROJECT_CONTEXT.md`, `../../../AGENTS.md` and `../../../WIKI.md` when present; otherwise verify facts from public source/configuration. These three root files stay local and untracked, outside wheel/Docker payloads; their template counterparts stay public. Check distributions with and without local copies and preserve their on-disk bytes when untracking.
+Keep the root context/history about this kit; keep template project facts uninitialized.
+For a procedure change, update current maintainer commands, this pointer contract, and relevant implementation docs in the same task.
+When verified facts or agreements change, synchronize this skill's scope/procedure/pointers and WIKI with the context; keep actual facts in context.
+Validate templates/links/registry, the agent registry (integrations/agents.json), and behavioral installation scenarios; record root CHANGELOG entries. Keep the root SKILL.md (the repository as a skill) consistent with the CLI, presets, extras, and policies.
+Review explicit semantic acceptance and future-upgrade conflicts whenever installer baseline behavior changes.
+Check candidate draft preservation, state/settings validation, and adapter retirement conflicts when changing installation. Exercise installed Git visibility and portable linked-path refusal; distinguish synthetic fixtures from real application trials. Verify the conditional Docker trigger in installed AGENTS and preserve edited entry points during upgrades.
+Exercise file-versus-directory native rule layouts on both probe and selected-write paths: simulate POSIX ENOTDIR on Windows, preserve existing file markers and rerun stability, and refuse blocked selected parents before writes. Do not hide permission failures or linked-path refusals during optional adapter probes; see [file-parent compatibility](../../../docs/ADAPTER_PATH_FIX.md).
+Exercise manifest-based profile detection and project-fact drafts (version/commands into PROJECT_CONTEXT and project.json), scoped Node/Python ignore rules, the installed-project doctor report, opt-in extras (session-start, guards, CI) including key-level client settings merges, legacy whole-file migration, and hook execution, client detection markers, interactive/check onboarding, the adr/changelog helpers, and the offline router helper (route/configure with provider selection) when installer behavior changes.
+For generated client configuration, exercise private/team settings files and mode switches, owned-entry moves, project.json precedence, secret lists, ignore blocks, every scoped rule format with root modules and skipped paths, presets that turn extras off, and workflow skill copies; recheck client formats against primary docs before changing them.
+For routing, compare the implementation ladder with canonical POLICY, exercise English/Russian operation/risk regressions and override precedence, provider-review status/sources, and distinguish recommendations from executed model controls. For stack profiles, exercise manifest evidence, module scoping, and command drafting; for Filament specifically test Composer dependency/lock evidence and source/native skill lifecycle. For optional metrics, verify failure/recovery accounting, missing-value coverage, duplicate/lock/path guards, private/team journal visibility, schema 1/2 compatibility, experiment/arm/task identity, per-provider analyze output, and upgrade preservation. Exercise context snapshots and doctor warnings for new/removed modules, profile drift, and manifest changes. Exercise adapter reports plus explicit retirement of unchanged files, backups/state updates, and modified-file conflicts. Exercise opaque evaluator pair coverage without task-text persistence. Use the [evaluation protocol](../../../docs/EVALUATION.md) for separately authorized application trials; synthetic fixtures establish no savings.
+Record actual OS/runtime and unavailable checks in the implementation record; keep source visibility checks separate from client activation.
+For measurement-led changes, test schema 1/2/3 compatibility, fixed A/B controls, immutable Git blobs and isolated repeated workspaces, missing/estimated telemetry, semantic-review gates, interrupted runs and idempotent private exports. Exercise resume identity checks, per-unit failure recording and configurable kit-arm agents/presets. Check that worker Git discovery cannot reach the source through parents: a ceiling at cwd itself is ineffective. Keep worker requests separate from observed execution. Exercise routing modes/pins/profiles, distinct-case quality floors, matched history, unsupported controls, immutable proposal history and explicit backed-up restore. Exercise module context scope, duplicate content, critical rules/ADRs above byte budgets and linked paths. Follow [the staged plan](../../../docs/DEVELOPMENT_PLAN.md) and [worker contract](../../../docs/BENCHMARK.md); defer live adapters/orchestration until their mechanisms and total coordination costs are verified.
+Resolve temporary fixture roots before deriving paths used by guards, assertions, or injected failures. Test equivalent path spellings; keep cleanup bound to original disposable directories. [Windows CI regression](../../../docs/WINDOWS_CI_FIX.md) records the relevant scenario.
+For reference upgrades, check the actual published tree and old paths left by overlays. Compatibility pointers link to canonical owners; never hide broken legacy links from the checker.
+When editing onboarding docs, verify examples against the actual CLI/defaults and preserve links to policy owners. Keep installation, native discovery, and measured execution claims distinct. For [OpenRouter documentation](../../../README.md#working-with-openrouter), recheck primary API/cache/usage docs; distinguish shipped context manifests from proposed request assembly/runtime, prompt caching from response reuse, and observed usage from assumed savings. Root README and Docker Hub Overview have no size quota; retain scoped instruction budgets and normal link/language checks.
+For [PyPI releases](../../../docs/PYPI.md), verify wheel/sdist metadata, VERSION, licenses, description, resources and private/path exclusions; build the wheel from sdist and smoke-install offline. Quote complete Twine globs; report OS gaps. A JSON 404 does not prove name eligibility; verify publisher registration. Test identity guards without uploads; preserve CI names and existing release tags. Use a new patch when an old tag predates publication support. Trusted Publishing stays manual/build-only by default, with exact version/tag/repository gates, OIDC only in upload jobs and validated same-run artifacts; setup and publication are separate. Keep MCP posture separate from live client activation.
+For repository administration or changes to existing required CI names, consult [repository maintenance](../../../CONTRIBUTING.md#repository-maintenance), verify live protection and emitted names, and keep required checks aligned. New local jobs establish no hosted result or required-check update. Remote changes need explicit authorization; Core governs commits/pushes.
+For every task assess [Docker image impact](../../../docs/DOCKER.md#change-impact-and-image-refresh), including packaged instructions and defaults. Follow canonical [image freshness](../../../template/ai-kit/CONTAINERS.md#image-freshness); rebuild/test affected final sources as ai-kit:dev or record why no rebuild is needed. For the image, verify actual client/daemon, pinned build inputs, VERSION/label identity, closed context, wheel resources, non-root bind permissions, read-only/offline preview and apply, preservation, conflicts, rerun and SIGTERM. Validate the Job schema; distinguish cluster/runtime coverage. Record test cache/volume ownership and size; follow canonical cleanup without shared-builder pruning. Keep image publication separate.
+For [dialogue memory](../../../docs/DIALOGUE_MEMORY.md), test all supported imports, selected ChatGPT branches, omissions, untrusted roles, pending prose, explicit keyed conflicts/resolutions, source-bound review, immutable reruns, both exports and byte limits. Exercise linked/blocked paths, private/team upgrade preservation, Git/build/package exclusions and installed CLI execution. Do not infer semantic agreement from no keyed conflicts or claim live sync/upload from local export. Preserve raw sources and default project context.
+For optional upstream skills, follow [security-audit](../../../docs/SECURITY_AUDIT.md) and [Strix integration](../../../docs/STRIX.md): preserve pinned bytes/license and newline attributes, verify bounded tree coverage/digests and nested-path aliases, explicit-only metadata, absent default/preset payloads, independent persistent choices, local adaptations/conflicts, links, visibility and wheel resources. Exempt only verified external examples from authored model/language/budget checks. Keep installation separate from audits/runtime setup; report unsupported validators. For Strix, check writable copy isolation, explicit full/diff scope, budget/data destination and no implicit cloud fallback; integration tests must start no scan, model or container.
+For [Context7](../../../docs/CONTEXT7.md), check opt-in skill/registry selection, independent persistence, source/native copies, local conflicts and unchanged native MCP configuration. Keep normal skill discovery, version-aware sanitized queries and remote activation separate. Recheck client schemas/authentication against primary docs; a source revision does not pin the hosted service.
+For [Web Design](../../../docs/WEB_DESIGN.md), check whole-module default absence, multi-entry skill selection, independent persistence, created-once project documents, native copies/retirement, local conflicts and linked/blocked paths. Exercise workflow context scope, required design memory above budgets, plain HTML without assumed stack facts, private raw output/team visibility and offline wheel resources. Keep TypeUI/SkillUI setup and real browser/Laravel acceptance separate from installer evidence; adopt external guidance only within the selected stack/visual system.
+For an explicitly requested release version, update VERSION, the root changelog, README release pointer, WIKI and maintainer context together; keep release history out of project templates. Recheck CLI version, kit validation and wheel metadata/install; build in an isolated source copy and exercise preservation across the prior-version baseline. State which behavioral results preceded release labeling; publication/tagging remain separate actions under Core. In release notes, distinguish Web Design instructions from external tools and generated-site acceptance, Context7 setup from installation, and OpenRouter guidance from a live adapter; verify security examples against pinned contracts.
+For every Docker image release, follow the [Docker Hub checklist](../../../CONTRIBUTING.md#docker-hub-releases) and update the complete [Overview](../../../docs/DOCKER_HUB_OVERVIEW.md); synchronize version/features/examples before building and verified publication identity afterward.
+For the current Docker/privacy release, follow [v1.4.1 preparation](../../../docs/V1_4_1.md); keep local image identity distinct from a registry digest and source-bound human review distinct from automatic conversation synchronization. After explicitly authorized publication, read back the registry digest, platform and version/configuration; preserve the prepared image and record later publication-only documentation separately. Do not assign additional tags implicitly.
+Do not bootstrap the reference repository as an application or imply native/runtime checks passed from static validation.

ai_kit_python-1.4.2/.agents/skills/python-work/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: python-work
+description: Apply project Python rules when changing confirmed Python scripts, packages, or tests.
+---
+
+# Python work
+
+Read [contribution rules](../../../CONTRIBUTING.md) and optional local `../../../PROJECT_CONTEXT.md`, then [Python rules](../../../ai-kit/stacks/PYTHON.md) and relevant [engineering rules](../../../ai-kit/ENGINEERING.md). Check the supported Python version, dependency format, script entry points and test commands before editing. Apply only to confirmed Python work.

ai_kit_python-1.4.2/.dockerignore

@@ -0,0 +1,90 @@
+# Closed build context: kit sources only, never an application or personal configuration.
+**
+!Dockerfile
+!.dockerignore
+!.gitignore
+!.gitattributes
+!VERSION
+!LICENSE
+!README.md
+!CHANGELOG.md
+!SECURITY.md
+!SKILL.md
+!BOOTSTRAP_PROMPT.md
+!CONTRIBUTING.md
+!Makefile
+!pyproject.toml
+!MANIFEST.in
+!aikit_cli.py
+!__init__.py
+!scripts/
+!scripts/*.py
+!tests/
+!tests/*.py
+!tests/fixtures/
+!tests/fixtures/**
+!template/
+!template/**
+!templates/
+!templates/**
+!integrations/
+!integrations/**
+!docs/
+!docs/**
+!ai-kit/
+!ai-kit/**
+!.agents/
+!.agents/skills/
+!.agents/skills/**
+!.github/
+!.github/workflows/
+!.github/workflows/check-kit.yml
+!.github/workflows/publish-pypi.yml
+!docker/
+!docker/build-requirements.txt
+!docker/pypi-requirements.txt
+!docker/check_version.py
+!deploy/
+!deploy/k8s/
+!deploy/k8s/*.yaml
+
+# These exclusions win even inside an allowed source directory.
+**/.git
+**/.git/**
+**/.env
+**/.env.*
+**/.aws
+**/.aws/**
+**/.codex
+**/.codex/**
+**/.claude
+**/.claude/**
+**/.secrets
+**/.secrets/**
+**/auth.json
+**/.netrc
+**/.pypirc
+**/*.pem
+**/*.p12
+**/*.pfx
+**/id_rsa*
+**/id_ed25519*
+**/__pycache__
+**/__pycache__/**
+**/*.py[cod]
+**/*.egg-info
+**/*.egg-info/**
+**/build
+**/build/**
+**/dist
+**/dist/**
+ai-kit/.metrics
+ai-kit/.metrics/**
+ai-kit/.memory
+ai-kit/.memory/**
+ai-kit/.upstream-cache
+ai-kit/.upstream-cache/**
+ai-kit/.design
+ai-kit/.design/**
+docs/.private
+docs/.private/**

ai_kit_python-1.4.2/.gitattributes

@@ -0,0 +1,3 @@
+# Pinned third-party bytes must survive Windows checkout without newline conversion.
+template/ai-kit/vendor/security-audit/** -text
+template/ai-kit/vendor/strix/** -text

ai_kit_python-1.4.2/.github/workflows/check-kit.yml

@@ -0,0 +1,70 @@
+name: Check AI-KIT
+
+on: [push, pull_request, workflow_dispatch]
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python: ['3.10', '3.13', '3.14']
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7, verified 2026-10-08
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7, verified 2026-10-08
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Validate files and Git visibility
+        run: python scripts/check_kit.py
+      - name: Exercise the unified CLI
+        run: python aikit_cli.py route "implement a feature"
+      - name: Exercise installation, upgrade, and evidence behavior
+        run: python -m unittest discover -s tests -v
+
+  wheel:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python: ['3.10', '3.14']
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7, verified 2026-10-08
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7, verified 2026-10-08
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Install reviewed build tools
+        run: python -m pip install --require-hashes -r docker/build-requirements.txt
+      - name: Install release validation tools
+        run: python -m pip install -r docker/pypi-requirements.txt
+      - name: Build a source archive and portable wheel
+        run: python tests/build_distribution.py "${{ runner.temp }}/pypi-dist"
+      - name: Validate archive metadata, privacy and resources
+        run: python scripts/check_distribution.py archives "${{ runner.temp }}/pypi-dist"
+      - name: Validate the package description
+        run: python -m twine check --strict "${{ runner.temp }}/pypi-dist/*"
+      - name: Smoke-install the wheel in an isolated environment
+        run: python tests/wheel_smoke.py "${{ runner.temp }}/pypi-dist"
+
+  docker:
+    name: Docker CLI
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97
+        with:
+          python-version: '3.13'
+      - name: Build the local CLI image
+        run: docker build --build-arg AIKIT_VERSION="$(cat VERSION)" --tag ai-kit:ci .
+      - name: Exercise offline container behavior and build-context boundaries
+        run: python tests/docker_smoke.py ai-kit:ci --context .

ai_kit_python-1.4.2/.github/workflows/publish-pypi.yml

@@ -0,0 +1,108 @@
+name: Prepare or publish Python package
+
+on:
+  workflow_dispatch:
+    inputs:
+      destination:
+        description: Build only, or explicitly upload to the selected registry
+        type: choice
+        options: [validate, testpypi, pypi]
+        default: validate
+        required: true
+      version:
+        description: Exact VERSION confirmation; required for either upload
+        type: string
+        default: ''
+        required: false
+
+permissions:
+  contents: read
+
+concurrency:
+  group: python-package-${{ github.ref }}-${{ inputs.destination }}
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
+        with:
+          python-version: '3.13'
+      - name: Verify explicit release identity before building
+        env:
+          RELEASE_VERSION: ${{ inputs.version }}
+          DESTINATION: ${{ inputs.destination }}
+        run: >-
+          python scripts/check_distribution.py identity
+          --expected-version "$RELEASE_VERSION" --destination "$DESTINATION"
+          --ref "$GITHUB_REF" --repository "$GITHUB_REPOSITORY"
+      - name: Validate sources and behavior
+        run: |
+          python scripts/check_kit.py
+          python -m unittest discover -s tests -v
+      - name: Install reviewed build and validation tools
+        run: |
+          python -m pip install --require-hashes -r docker/build-requirements.txt
+          python -m pip install -r docker/pypi-requirements.txt
+      - name: Build source archive and wheel from that source archive
+        run: python tests/build_distribution.py "${{ runner.temp }}/pypi-dist"
+      - name: Validate archives, description and installed CLI
+        run: |
+          python scripts/check_distribution.py archives "${{ runner.temp }}/pypi-dist"
+          python -m twine check --strict "${{ runner.temp }}/pypi-dist/*"
+          python tests/wheel_smoke.py "${{ runner.temp }}/pypi-dist"
+      - name: Retain the exact validated distributions
+        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2, verified 2026-10-16
+        with:
+          name: python-distributions
+          path: ${{ runner.temp }}/pypi-dist/*
+          if-no-files-found: error
+          retention-days: 14
+
+  testpypi:
+    needs: build
+    if: inputs.destination == 'testpypi' && github.repository == 'tigusigalpa/ai-kit' && startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/project/ai-kit-python/
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2, verified 2026-10-16
+        with:
+          name: python-distributions
+          path: dist/
+      - name: Upload only the validated artifacts to TestPyPI
+        uses: pypa/gh-action-pypi-publish@dc37677b2e1c63e2034f94d8a5b11f265b73ba33 # v1.14.2, verified 2026-10-16
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          packages-dir: dist/
+          attestations: true
+          skip-existing: false
+
+  pypi:
+    needs: build
+    if: inputs.destination == 'pypi' && github.repository == 'tigusigalpa/ai-kit' && startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/ai-kit-python/
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2, verified 2026-10-16
+        with:
+          name: python-distributions
+          path: dist/
+      - name: Upload only the validated artifacts to PyPI
+        uses: pypa/gh-action-pypi-publish@dc37677b2e1c63e2034f94d8a5b11f265b73ba33 # v1.14.2, verified 2026-10-16
+        with:
+          repository-url: https://upload.pypi.org/legacy/
+          packages-dir: dist/
+          attestations: true
+          skip-existing: false

ai_kit_python-1.4.2/.gitignore

@@ -0,0 +1,60 @@
+# Reference repository: version instruction sources and project templates.
+# Application projects receive templates/gitignore.private or gitignore.team instead.
+
+# ---- Local AI-KIT and agent state ----
+/AGENTS.md
+/PROJECT_CONTEXT.md
+/WIKI.md
+/ai-kit/.upstream-cache/
+/ai-kit/.metrics/
+/ai-kit/.memory/
+/.claude/
+/.codex/
+/.windsurf/
+/.codeium/
+/.devin/
+/.cursor/
+/.kimi/
+/.manus/
+/.deepseek/
+/.qoder/
+/.grok/
+# Extracted AI-KIT bundles; the hyphen keeps ai-kit/ itself visible on case-insensitive systems.
+/AI-KIT-*/
+/ai-kit-*/
+
+# ---- Local secrets ----
+.env
+.env.*
+!.env.example
+/.secrets/
+
+# ---- Python development caches ----
+/.cache/
+/.venv/
+__pycache__/
+*.py[cod]
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+/.test-results/
+dist/
+build/
+*.egg-info/
+*.log
+
+# ---- IDE, editor, and OS files ----
+.idea/
+.vscode/
+.fleet/
+.zed/
+.nova/
+.history/
+*.swp
+*.swo
+*~
+.DS_Store
+Thumbs.db
+Desktop.ini

ai_kit_python-1.4.2/BOOTSTRAP_PROMPT.md

@@ -0,0 +1,18 @@
+# New-project start prompt
+
+Give the following English prompt to an agent with the AI-KIT distribution and target repository available:
+
+~~~text
+Analyze this repository and install or adapt the attached AI-KIT.
+Read template/ai-kit/BOOTSTRAP.md from the distribution, then inspect the target's current instructions and manifests.
+Use scripts/install.py for a preview and apply only a compatible, reviewed plan; preserve existing files and decisions.
+Keep the supplied defaults unless I explicitly change them.
+After installation read the target AGENTS.md, ai-kit/CORE.md, and current PROJECT_CONTEXT.md.
+Enable only confirmed stack profiles and record module paths, evidence, and actual check commands.
+Run relevant checks, review the changes, and update project context, continuity pointers, and CHANGELOG.
+Report what changed, conflicts, and checks that remain unavailable.
+~~~
+
+When AI-KIT is already installed, run the installed ai-kit-bootstrap skill instead: /ai-kit-bootstrap in Claude Code, $ai-kit-bootstrap in Codex.
+
+For a file-access-limited chat, attach the relevant template files and current project evidence. An agent must not claim filesystem installation without access.

ai_kit_python-1.4.2/CHANGELOG.md

@@ -0,0 +1,85 @@
+# AI-KIT changelog
+
+## v1.4.2 (2026-10-16)
+
+- Verified kit/archive/offline installation, 351 Linux tests (two skips), 23 Windows CLI/archive tests and Docker smoke. [Evidence](docs/V1_4_2.md).
+- Prepared `ai-kit-python` 1.4.2; PyPI publisher/GitHub pypi environment verified. Preserve v1.4.1 Git/Docker. [Status](docs/V1_4_2.md).
+- Fixed quoted Twine wildcards for Windows CI.
+- Added PyPI metadata, a portable [description](docs/PYPI_DESCRIPTION.md), README guidance and a [release procedure](docs/PYPI.md). Wheel/sdist checks cover metadata, licenses, resources, private files, offline installation and publication identity. Manual Trusted Publishing defaults to validation, requires exact version/tag/repository, and gives OIDC only to upload jobs consuming tested artifacts. Required CI names stay unchanged.
+- Isolated builds inject synthetic private probes; archives exclude private drafts and credential filenames. Added tested `aikit --version`; published Docker 1.4.1 examples use its existing `--help`. Added a README Docker Hub badge.
+
+- Saved the complete [Docker Hub Overview](docs/DOCKER_HUB_OVERVIEW.md) for v1.4.1 and linked it from README/Docker docs. The [release checklist](CONTRIBUTING.md#docker-hub-releases) and continuity skill require updating it for every image release, with verified publication identity recorded after push. Exempted only this user-facing document from the size quota alongside README; instruction budgets remain unchanged, with regression coverage.
+
+## v1.4.1 (2026-10-15)
+
+- Added [image freshness](docs/DOCKER.md#change-impact-and-image-refresh): maintainer and installed AGENTS assess Docker impact, rebuild/test affected images and preserve publication authorization.
+- Keep root maintainer AGENTS/PROJECT_CONTEXT/WIKI local and untracked; retain template counterparts. Exclude local copies from Git, wheel and Docker; validate distributions without them.
+
+- Prepared matching VERSION, wheel and Docker version 1.4.1; [release checks and publication record](docs/V1_4_1.md). Added package/context regression coverage and retained full v1.2.0 history in its archive.
+
+- Published `tigusigalpa/ai-kit:1.4.1`; push, remote digest/configuration and anonymous tag visibility matched the tested image. Post-label: nine Windows CLI tests, 339 Linux tests (337 passed/two skips), Docker smoke, offline wheel/source privacy checks and private/team 1.4.0 upgrades passed. [Evidence](docs/V1_4_1.md#verification).
+
+## v1.4.0 (2026-10-15)
+
+- Published `tigusigalpa/ai-kit:1.4.0` to Docker Hub at the owner's request. Remote digest, linux/amd64 platform, version label and non-root entrypoint were read back and matched the prepared image; [publication record](docs/V1_4_0.md#docker-hub-publication). No `latest` tag was assigned.
+- Prepared v1.4.0 for the Docker CLI and local dialogue memory. VERSION, CLI/wheel metadata, image label and release pointers use the same version; [release checks and Docker Hub handoff](docs/V1_4_0.md). Registry publication and Git tagging remain separate.
+- Added offline `aikit memory import|merge|export`: three dialogue formats, selected ChatGPT branches, source-bound human review, explicit contradictions and ChatGPT/OpenRouter reference exports. Preserves immutable artifacts, refuses unreviewed normal exports and protects private memory across upgrades/builds. Added tests and detailed [workflow](README.md#shared-context-from-two-dialogues)/[contract](docs/DIALOGUE_MEMORY.md). Automatic sync and API execution remain separate. Archived v1.1.0 history without dropping its text.
+- Before release labeling, dialogue-memory verification passed: 336 Windows tests (329 passed/seven environment skips), 336 packaged Linux tests (334 passed/two skips), clean kit validation, offline wheel and private-package exclusion, README conflict-resolution flow and Docker smoke. [Coverage and limits](docs/DIALOGUE_MEMORY.md#verification).
+- Added standalone non-root Docker CLI, pinned build inputs, offline wheel resources, application mounts, Kubernetes preview Job, smoke tests, CI and [usage/results](docs/DOCKER.md). Earlier Docker-only Windows and packaged Linux runs passed 309 tests (307 passed/two skips each); actual image, preservation, signals, context exclusions, wheel and schema checks passed.
+- After labeling: nine CLI tests, 336 packaged Linux tests (334 passed/two Windows-only skips), clean kit validation, isolated Windows wheel/fresh-venv smoke and private-memory exclusion passed. The actual linux/amd64 image passed Docker smoke. Tracked 1.3.0 upgrades in private/team modes preserved data and pin identities, with explicit review of a local skill conflict; reruns stayed stable. [Release evidence](docs/V1_4_0.md#verification).
+
+## v1.3.0 (2026-10-13)
+
+- Prepared v1.3.0 for optional Web Design and the expanded README guide. The 304-test behavioral discovery below preceded release labeling; publication/tagging remain separate. [Release checks](docs/WEB_DESIGN.md#release-labeling).
+- After labeling: eight CLI tests, version/wheel metadata 1.3.0, clean kit checks and offline fresh-venv wheel smoke passed. The pre-label 1.2.0 upgrade preserved facts, settings, local design/skill edits, MCP configuration and both security pins; rerun stayed stable.
+- Added optional Web Design: --with-web-design installs four short skills, conditional Blade/library/tool/review guides and created-once project design documents. Added scoped context workflows, source/Claude lifecycle and preservation tests; installation remains offline. [Guide](README.md#web-design), [integration record](docs/WEB_DESIGN.md).
+- Removed the root README size quota and added extensive reference-to-site instructions for Laravel, Tailwind, Bootstrap, Alpine/Livewire, daisyUI, Flowbite, Flux, TypeUI and SkillUI. Existing instruction budgets remain scoped; external setup and real application checks stay separate.
+- Verified on Windows/Python 3.12.14: 304 tests (300 passed/four runtime skips), clean kit/skill checks, all-client private/team visibility, preserved tracked 1.2.0 upgrade and fresh-venv wheel smoke. Live tools/sites remain unverified. Archived v0.6.4 history without losing its text; [details](docs/WEB_DESIGN.md#verification).
+
+## v1.2.0 (2026-10-12)
+
+[Archived release entry](docs/history/v1.2.0-changelog.md#v120-2026-10-12).
+
+## v1.1.0 (2026-10-12)
+
+[Archived release entry](docs/history/v1.1.0-changelog.md#v110-2026-10-12).
+
+## v0.13.0 (2026-10-11)
+
+- Added Rust, .NET, Java (Maven/Gradle), and Terraform/Helm stack profiles with evidence-based per-module detection: Cargo.toml (rust-version, cargo test/build/clippy), *.csproj/*.fsproj/*.vbproj and global.json (TargetFramework, dotnet test/build), pom.xml/mvnw/build.gradle(.kts)/gradlew (language level, wrapper-aware commands), and .tf files or Chart.yaml (fmt/validate, helm lint). Drafts remain suggestions until bootstrap confirms them.
+- Added rust-work, dotnet-work, java-work, and infra-work skills to the registry; Claude native copies install with the claude agent selection.
+- Benchmark packs accept the new stack names; README, SKILL.md, and WIKI profile lists updated.
+- Verified locally (Windows/Python 3.14.6): 254 tests ran, all passed, 1 runtime skip; kit validation returned zero errors and zero warnings; Python 3.10 grammar verified; end-to-end smoke detected RUST/INFRA with drafted context and installed source/native skills. Real applications of the new stacks remain untrialed.
+
+## v0.12.0 (2026-10-11)
+
+- Benchmark packs accept optional `kit_agents`/`kit_preset` (default codex/minimal), so kit arms install the client's real adapter set and preset instead of a hard-coded arm; both are validated against the installer registry.
+- Benchmark task paths are now probed against the benchmark project instead of the process working directory.
+- Interrupted benchmark runs are resumable: re-running `benchmark run` with the identical pack skips completed units and continues missing ones, and a changed pack is refused against the existing run. Per-unit infrastructure failures are recorded as explicit failed units, so one bad unit neither aborts the run nor hides as an executed attempt; failed units still block savings and cannot be reviewed as correct.
+- The unified `aikit` dispatcher now prefers installed `aikit.scripts.*` package modules over bare script-path imports, avoiding duplicate module objects inside the wheel.
+- The checker document budgets are named constants; the root README budget rises to 22000 bytes (human onboarding that never enters project context), other documents keep 12000.
+- Verified locally (Windows/Python 3.14.6): 252 tests ran, all passed, 1 runtime skip; kit validation returned zero errors and zero warnings; Python 3.10 grammar was verified for the changed sources. Live workers, native client activation and hosted CI remain unverified.
+
+## v0.11.0 (2026-10-11)
+
+- Fixed provider/model overrides carrying inherited effort; synchronized Gemini routing policy with the reviewed registry. Existing selection/settings defaults stay readable and unchanged.
+- Fixed the untested v0.10 adapter audit failing before it could report file-blocked native paths. Read-only state validation now allows obstructions after strict link/boundary checks; installation writes retain their refusal guards.
+- Forwarded subcommand help to the actual command parser, so `aikit benchmark --help` and install flags are discoverable.
+- Added preview-first `aikit benchmark run|review|report|export`: immutable Git blobs, separate A/B/C workspaces/repeats, equal fixed A/B controls, a configured worker protocol, actual-telemetry coverage, checks plus explicit semantic review, private JSON/Markdown reports and idempotent journal export. No live vendor adapter or application savings is claimed.
+- Added metric schema 3 for revision/case/repetition/stack/class/level/capability/review strata, keeping schemas 1/2 readable. Comparisons require matched reviewed tasks and actual single-currency costs, include all failures/retries and refuse lower-quality/unknown/estimated spend claims. Added per-stack analysis.
+- Added optional manual/fixed/recommended/adaptive modes, task/project pins and economy/balanced/quality profiles. Learned recommendations require comparable distinct-case samples and quality floors; unsupported controls or insufficient evidence retain the capability recommendation. Immutable proposals preserve prior selection and support explicit backed-up restore without automatic policy writes.
+- Added read-only module context selection, duplicate detection and byte-budget reporting while preserving critical requirements and architectural decisions. Added staged acceptance plan and orchestration research in ADR 0012.
+- Expanded wheel resources and smoke checks outside the source checkout, including installed validation, new command imports and context selection. Windows/Python 3.12.14 full discovery ran 248 tests (244 passed, four runtime skips); post-review checks and offline wheel installation passed; kit validation returned zero errors/warnings. [Results and limits](docs/IMPLEMENTATION.md#measurement-led-development-verification).
+
+## v0.6.4 (2026-10-10)
+
+[Archived release entry](docs/history/v0.6.4-changelog.md#v064-2026-10-10).
+
+## v0.5.0 (2026-10-10)
+
+[Archived release entry](docs/history/v0.5-changelog.md#v050-2026-10-10).
+
+## Earlier kit
+
+Release history is preserved: [v0.5.0](docs/history/v0.5-changelog.md), [v0.10.0](docs/history/v0.10-changelog.md), [v0.6.5-v0.9](docs/history/v0.6.5-v0.9-changelog.md), [v0.4.5-v0.4.7](docs/history/v0.4-changelog.md), [v0.3.3-v0.3.8](docs/history/v0.3-changelog.md), [v0.2-v0.2.2 and Windows fixtures](docs/history/v0.2-changelog.md), and [v0.1](docs/history/v0.1-changelog.txt). Old paths and language/router agreements are historical data.
+[Prior routing decision](docs/adr/0001-adaptive-model-routing.md) records the accepted routing baseline; this changelog is not copied into projects.

ai_kit_python-1.4.2/CLAUDE.md

@@ -0,0 +1,3 @@
+# AI-KIT maintainer entry
+
+@AGENTS.md

ai_kit_python-1.4.2/CONTRIBUTING.md

@@ -0,0 +1,46 @@
+# Contributing
+
+Read [Core](template/ai-kit/CORE.md) and [policy ownership](docs/IMPLEMENTATION.md#policy-ownership).
+Make a coherent local change, add behavioral checks for installer or validator risks, and run the documented checks.
+Keep project templates free of maintainer facts/history. Preserve local-file ownership and authorization boundaries.
+Update the root changelog; record significant design decisions in docs/adr/.
+Discuss version/provider changes using current primary documentation and actual runtime evidence. Commit/push authorization follows Core.
+
+## Local maintainer files
+
+Root `AGENTS.md`, `PROJECT_CONTEXT.md` and `WIKI.md` are optional local maintainer files. Keep them on disk, ignored and untracked; do not copy their contents into public documents or build artifacts. Read them when present and preserve local agreements. Otherwise establish current facts from VERSION, pyproject, source and the public guides. Their `template/` counterparts are distribution sources and remain tracked for application installation.
+
+Ignore rules do not untrack existing files. Use `git rm --cached -- AGENTS.md PROJECT_CONTEXT.md WIKI.md` to stop tracking only the root copies while keeping them on disk. This stages removal for a later authorized commit; it does not erase earlier history. Do not force-add local copies. Public documents and checks must work without them; wheel and Docker builds exclude them even when present.
+
+## Maintainer workflow
+
+Follow plan -> implement -> test -> review -> document. Run `python scripts/check_kit.py` and `python -m unittest discover -s tests -v` for affected installer/checker behavior. When packaging changes, build from an isolated source copy and smoke-install the wheel. Review preservation, conflicts, links, visibility and upgrades; report unavailable checks.
+
+Assess [Docker impact](docs/DOCKER.md#change-impact-and-image-refresh) on every task and rebuild/test affected final sources locally. Publication needs authorization. Update the root changelog, any local context/map and the continuity skill when procedures change. Keep templates free of kit history; do not bootstrap this distribution as an application.
+
+## Docker Hub releases
+
+Update [DOCKER_HUB_OVERVIEW.md](docs/DOCKER_HUB_OVERVIEW.md) for every AI-KIT Docker image release, including patch releases and authorized replacements of an existing tag. Keep the complete publication copy in that file; README and the [Docker guide](docs/DOCKER.md) link to it.
+
+Before building, synchronize its version/tag, feature summary, release changes, optional modules, CLI examples and runtime/platform contract with VERSION, README and actual sources. Record only checks that ran. After an authorized push, read back the remote digest and configuration, then update publication status and the immutable pull example from that evidence. Never invent a digest or claim local preparation is publication. Keep descriptive publication receipts separate from the prepared image snapshot; do not rebuild/replace an image just to include its own digest.
+
+The root README and Docker Hub Overview are user documentation without a size quota. Other document and instruction budgets remain scoped. Preparing this file does not itself publish a Docker Hub description, image or Git release; the relevant authorization still applies.
+
+## Python package releases
+
+Follow [PyPI preparation and release](docs/PYPI.md) for every package release. Synchronize VERSION, pyproject metadata, [description](docs/PYPI_DESCRIPTION.md) and README; verify license/resource inclusion and local-file exclusions in both sdist and wheel, build the wheel from sdist, run strict Twine checks and offline fresh-venv smoke. Preserve existing CI matrix/job names. Refresh the image when packaging changes affect it.
+
+Trusted Publishing remains manual and build-only by default. Registry uploads require the matching version/tag, canonical repository and the separately configured registry environment/publisher. Build tests have no OIDC permission; upload jobs consume only validated same-run artifacts. Record local, hosted and registry results separately. No upload, publisher/account setup or Git operation is authorized by preparation alone.
+
+## Repository maintenance
+
+Before changing remote protection or required CI checks, verify live configuration and emitted names. Local jobs establish neither hosted success nor updated protection. Remote changes, commits, pushes and publication need the relevant user authorization. Private context snapshots require verification before use.
+
+## Updating a reference repository
+
+Archive overlays leave old files behind. Compatibility pointers retain known v0.1 rule paths.
+Overlay the bundle at the reference root, preserve customizations, and run the checker.
+
+The obsolete .gitignore_real is historical material: its useful rules live in the templates/ policies, scoped by the installer where a global rule would hide project source (Composer vendor, Moodle config.php, Node and Python output). Use templates/ policies for applications.
+Keep the root [SKILL.md](SKILL.md) current when commands, options, or features change.
+Retire old pointers after reviewing inbound links and local changes.

ai_kit_python-1.4.2/Dockerfile

@@ -0,0 +1,44 @@
+# CLI runtime. Build with --build-arg AIKIT_VERSION=<VERSION file value>.
+FROM scratch AS context-audit
+COPY . /
+
+FROM python:3.13.16-slim-bookworm@sha256:a1165e272e578941b84abc79e4ab38a0305cd12803a5c4247979ac7655f4d641 AS wheel-builder
+ENV PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PYTHONDONTWRITEBYTECODE=1
+WORKDIR /build/source
+ARG AIKIT_VERSION
+COPY VERSION ./VERSION
+COPY docker/check_version.py /build/check_version.py
+RUN python /build/check_version.py
+COPY docker/build-requirements.txt /build/build-requirements.txt
+RUN python -m pip install --require-hashes -r /build/build-requirements.txt
+COPY . .
+RUN python -m pip wheel . --no-index --no-deps --no-build-isolation --wheel-dir /build/wheels
+
+FROM python:3.13.16-slim-bookworm@sha256:a1165e272e578941b84abc79e4ab38a0305cd12803a5c4247979ac7655f4d641 AS runtime
+ARG AIKIT_VERSION
+LABEL org.opencontainers.image.title="AI-KIT CLI" \
+      org.opencontainers.image.description="Offline AI-KIT instructions, installer and project helpers" \
+      org.opencontainers.image.source="https://github.com/tigusigalpa/ai-kit" \
+      org.opencontainers.image.licenses="MIT" \
+      org.opencontainers.image.version="${AIKIT_VERSION}"
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONNOUSERSITE=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+RUN apt-get update \
+    && apt-get install --yes --no-install-recommends git \
+    && rm -rf /var/lib/apt/lists/* \
+    && groupadd --gid 10001 aikit \
+    && useradd --uid 10001 --gid 10001 --create-home --shell /usr/sbin/nologin aikit \
+    && mkdir -p /workspace \
+    && chown 10001:10001 /workspace
+COPY --from=wheel-builder /build/wheels /wheels
+RUN python -m pip install --no-index --no-deps /wheels/*.whl \
+    && rm -rf /wheels
+USER 10001:10001
+WORKDIR /workspace
+STOPSIGNAL SIGTERM
+ENTRYPOINT ["aikit"]
+CMD ["--help"]

ai_kit_python-1.4.2/KIMI.md

@@ -0,0 +1,3 @@
+# Kimi project entry
+
+Read `AGENTS.md` and the current `PROJECT_CONTEXT.md` before making changes. Open relevant rules through `WIKI.md`; maintain context and skills according to `ai-kit/SKILLS.md`. Supply this file explicitly if the environment does not read it automatically.