docpull 6.0.1

What's Changed

• Fix v6 publish and metrics automation by @zacharyr0th in #102
• Keep v6 publish scorecard checkout clean by @zacharyr0th in #103
• Persist benchmark config artifacts by @admin-raintree in #105
• chore(release): prepare 6.0.1 by @zacharyr0th in #106

Full Changelog: v6.0.0...v6.0.1

docpull 6.0.0

Published to PyPI: https://pypi.org/project/docpull/6.0.0/

Release validation: https://github.com/raintree-technology/docpull/actions/runs/28686812350 completed successfully, including build, A+ release gates, wheel smoke install, and trusted PyPI publish.

Product code tag: v6.0.0. Subsequent main commits only fixed release automation and metrics workflow hygiene.

What's Changed

• Publish governance baseline to main by @admin-raintree in #100
• Prepare v6.0.0 release by @zacharyr0th in #101

Full Changelog: v5.5.1...v6.0.0

docpull 5.5.1

DocPull v5.5: Typed Local Context Packs

v5.5.1 Hotfix

DocPull v5.5.1 ships the post-release fixes from the real-data validation pass:
screenshot-pack now works with the current agent-browser command contract,
and search-pack now writes replay config metadata across local, dry-run,
budget-blocked, and provider-backed paths.

v5.5.0

DocPull v5.5 adds local-first context packs for brand, design, product,
structured extraction, visual assets, screenshots, and search.

The release keeps the core DocPull boundary: async HTTP extraction stays the
default, browser rendering is explicit, provider-backed search is budgeted, and
every workflow writes durable local artifacts with provenance.

pip install docpull

docpull brand-pack example.com -o packs/brand
docpull styleguide-pack https://example.com -o packs/styleguide
docpull product-pack https://example.com/pricing -o packs/products
docpull extract-schema packs/products --schema schema.json -o packs/schema
docpull image-pack https://example.com -o packs/images
docpull search-pack "pricing" --provider local --pack-dir packs/products -o packs/search

New pack families include:

• brand-pack for evidence-backed brand profiles, social links, logo/icon
  candidates, colors, contacts, and cited local metadata.
• styleguide-pack for CSS variables, colors, font stacks, component samples,
  spacing, radii, and shadows without downloading remote fonts by default.
• product-pack for local Product/Offer JSON-LD, pricing rows, and cited
  product records.
• extract-schema for deterministic JSON Schema-shaped extraction from a URL
  or existing local pack.
• image-pack and screenshot-pack for visual evidence, with screenshot
  capture behind DOCPULL_RENDER_TRUSTED_BROWSER_TARGETS=1.
• search-pack for local pack search plus explicit provider dry-runs and
  budget-gated provider routes.

Every pack writes a result JSON, Markdown report, source_policy.json,
citations or basis records, replay config, pack metadata, and
run.accounting.json.

The useful claim is still narrow:

DocPull builds auditable, file-backed context from public sources before it
ever asks for a browser or a paid provider.

docpull 5.5.0

DocPull v5.5: Typed Local Context Packs

DocPull v5.5 adds local-first context packs for brand, design, product,
structured extraction, visual assets, screenshots, and search.

The release keeps the core DocPull boundary: async HTTP extraction stays the
default, browser rendering is explicit, provider-backed search is budgeted, and
every workflow writes durable local artifacts with provenance.

pip install docpull

docpull brand-pack example.com -o packs/brand
docpull styleguide-pack https://example.com -o packs/styleguide
docpull product-pack https://example.com/pricing -o packs/products
docpull extract-schema packs/products --schema schema.json -o packs/schema
docpull image-pack https://example.com -o packs/images
docpull search-pack "pricing" --provider local --pack-dir packs/products -o packs/search

New pack families include:

• brand-pack for evidence-backed brand profiles, social links, logo/icon
  candidates, colors, contacts, and cited local metadata.
• styleguide-pack for CSS variables, colors, font stacks, component samples,
  spacing, radii, and shadows without downloading remote fonts by default.
• product-pack for local Product/Offer JSON-LD, pricing rows, and cited
  product records.
• extract-schema for deterministic JSON Schema-shaped extraction from a URL
  or existing local pack.
• image-pack and screenshot-pack for visual evidence, with screenshot
  capture behind DOCPULL_RENDER_TRUSTED_BROWSER_TARGETS=1.
• search-pack for local pack search plus explicit provider dry-runs and
  budget-gated provider routes.

Every pack writes a result JSON, Markdown report, source_policy.json,
citations or basis records, replay config, pack metadata, and
run.accounting.json.

The useful claim is still narrow:

DocPull builds auditable, file-backed context from public sources before it
ever asks for a browser or a paid provider.

docpull 5.0.2

Added

• Add docpull share for serving generated Markdown, HTML, or plain text reports at a simple local URL.
• Keep sharing local-first by default with loopback-only binding, plus explicit --allow-network-bind for exposed report links.
• Expose SDK helpers create_report_server and render_report_document for tools that want to create shareable report URLs programmatically.

Verified

• Release workflow passed full gates and published the wheel and sdist to PyPI.

DocPull 5.0.1

DocPull 5.0.1 is a patch release for the v5 MCP and accounting surface.

Highlights:

• MCP structured responses now include non-secret run accounting receipts for budget-blocked provider/cloud routes and local pack answers.
• Responses include run.accounting.json artifact paths when a durable receipt was written.
• Package, plugin manifests, plugin README, and changelog metadata are synchronized to 5.0.1.

Validation:

• GitHub Publish to PyPI workflow passed for v5.0.1.
• PyPI release: https://pypi.org/project/docpull/5.0.1/

Install:

pip install --upgrade docpull

docpull 5.0.0

Added

• Add the local-first expansion surface: optional agent-browser rendering,
  provider-neutral discovery packs, source policy validation, pack refresh
  reports, pack audits, cited local answers, JSONL/agent exports, a
  localhost-only pack server, authenticated-source checks, and cron-friendly
  local monitors.
• Add a shared free-first budget contract with CLI --budget, SDK
  BudgetConfig, policy-file budget.maximum_paid_cost_usd, route
  explanations, stricter effective paid caps, and deterministic
  run.accounting.json artifacts for budgeted or paid-capable runs.
• Enforce fail-closed zero-dollar runs: local cache, direct HTTP, sitemap/static
  discovery, local extraction, local indexing, local pack intelligence, local
  monitors, and local agent-browser rendering remain available, while live
  Tavily, Exa, Parallel, Vercel Sandbox, E2B, provider probes, and paid-capable
  benchmark routes are blocked before execution.
• Add the Phase 2 zero-dollar benchmark mode and target set, including
  completion classes for complete_for_0, complete_with_local_browser,
  partial_for_0, requires_provider, requires_cloud_browser, and
  blocked_by_policy.
• Add provider-free discovery scanning with docpull discover scan URL for
  llms.txt, RSS/Atom feeds, OpenAPI references, richer sitemap discovery, and
  public GitHub documentation trees, all writing the standard
  candidate_sources.ndjson discovery-pack contract.
• Add Phase 4 escalation suggestions when local capture is partial, with local
  discovery/render commands first, BYOK provider dry-run/live commands next,
  cloud rendering last, and estimated paid request/cost guards before
  escalation.
• Add provider-neutral local parity workflows: docpull extract-pack,
  docpull map, docpull crawl-pack, docpull research-pack, and
  docpull entities-pack, plus SDK helpers and MCP tools over the same
  modules. These workflows write local lifecycle artifacts including
  events.ndjson, status.json, poll.report.json, and
  webhook.sample.json.
• Add local structured-output validation for docpull research-pack --schema
  using a dependency-free JSON Schema subset over cited local answer fields.
• Add monitor lifecycle controls: docpull monitor trigger, pause,
  unpause, and scheduler-snippet, plus monitor dedupe labels.
• Add MCP tools for local expansion workflows: render_url,
  discover_sources, fetch_discovered_sources, extract_pack,
  map_sources, crawl_pack, research_pack, entities_pack,
  refresh_pack, audit_pack, answer_pack, validate_policy,
  export_pack, and serve_pack_status.
• Add local downstream export formats for Sheets CSV/TSV, n8n workflow JSON,
  Vercel AI SDK JSON, CrewAI JSON, warehouse NDJSON, and optional Parquet via
  docpull[parquet].
• Add explicit optional-renderer diagnostics: docpull render --check,
  docpull render --agent-browser-bin, SDK
  check_agent_browser_availability(), doctor reporting for the external
  agent-browser runtime, and a live smoke test that skips when the executable
  is absent.
• Harden optional browser rendering by requiring HTTPS except localhost/loopback
  HTTP and rejecting non-default renderer action permissions.
• Add optional cloud sandbox render runtimes: Vercel through the Vercel Sandbox
  CLI and E2B through the E2B Python SDK/API key.
• Standardize cloud rendering on the same agent-browser --json contract as
  local rendering. Add docpull render --runtime local|vercel|e2b,
  docpull render init ..., docpull render doctor, estimated per-render
  budget caps, E2B template support, prebuilt sandbox install skipping, E2B
  file result transport, and opt-in live cloud smoke tests gated by
  DOCPULL_LIVE_CLOUD_RENDER=1.
• Add local pack intelligence commands: docpull pack citations,
  docpull pack entities, docpull pack search, and docpull pack brief,
  plus matching MCP tools for agent access to citation maps, structured
  signals, cited pack search, and cited briefs.
• Add docpull pack prepare, prepare_pack, and MCP pack_prepare to write
  the standard local pack intelligence bundle in one step.
• Post-process successful Parallel, Tavily, and Exa provider context packs with
  local score, source-score, citation, entity, search, and brief artifacts.
• Add first-class Tavily and Exa provider adapters plus docpull tavily ...
  and docpull exa ... aliases for context-pack and extract-pack workflows.
• Add a provider capability matrix and docpull tavily map-pack, which uses
  Tavily Map to write a standard DocPull discovery pack.
• Harden provider API key handling by rejecting unsafe key values before header
  use or local secret-file writes.
• Move provider capability metadata out of adapter code, split provider tests by
  key/adapter/CLI responsibility, and add auth path redaction for CI/agent logs.
• Add explicit provider live probes: Tavily account usage, Exa public team info,
  Parallel opt-in auth-gate validation, and guarded smoke probes separate from
  offline auth readiness.
• Add make test-inventory and make test-all-local so contributors can report
  default pytest, fully gated pytest collection, Bun MCP, and coverage gates
  separately.

Changed

• Reframe public docs around DocPull as a local-first, free-first evidence
  engine: local and open-data routes first, BYOK providers as explicit
  escalation, hosted execution as a future product boundary, and no hidden paid
  calls, CAPTCHA bypass, stealth scraping, or proprietary web-scale index
  claims.

Fixed

• Resolve discovery links against the final redirected URL so moved docs sites
  do not produce broken relative links.
• Prefer real streamed/hidden application content over loading skeletons when
  extracting modern docs pages, and remove loading-only placeholders from the
  selected content tree.
• Clean up stdio MCP child processes in tests so the full local gate does not
  leak servers after client failures.

docpull 4.4.1

Changed

• Remove the embedded README demo GIF from the PyPI long description so the project page stays focused on install and usage content.
• Raise optional MCP dependency floors for starlette and cryptography so release audits install patched versions.

Distribution

• PyPI: https://pypi.org/project/docpull/4.4.1/
• Wheel: docpull-4.4.1-py3-none-any.whl
• Source distribution: docpull-4.4.1.tar.gz

docpull 4.3.1

DocPull 4.3.1 tightens the public-web to agent-ready Markdown positioning across PyPI, GitHub, README, and the website.

Highlights:

• Updated package, repository, README, website, Open Graph, and structured metadata around public static/server-rendered web pages, Python, CLI/SDK, MCP, RAG, and agent context workflows.
• Added launch copy, comparison guidance, and marketing visibility research for developer, Python, MCP, and RAG discovery channels.
• Added launch assets: square logo variants, desktop/mobile screenshots, full-page capture, and a short website demo video.

Release artifacts were published to PyPI via trusted publishing: https://pypi.org/project/docpull/4.3.1/

docpull 4.0.1

A release-readiness patch that tightens the public product boundary. No runtime
API changes and no migration needed.

Changed

• Make the Python docpull mcp server the only documented supported MCP path
  for agents, plugins, Claude Code, Cursor, and Claude Desktop.
• Mark the root TypeScript/Bun mcp/ tree as an internal lab, make its package
  metadata private, and remove end-user install instructions for that path.
• Replace stale YAML example files with current CLI recipes so docs no longer
  advertise removed options such as --sources-file, TOON output,
  keep_variant, language, or create_index.
• Update website examples and performance copy to match the current CLI and
  benchmark results.