Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

Release v0.21.0

Louis Choquel96baf5d8fe2a
diff --git a/.claude/skills/release/SKILL.md b/.claude/skills/release/SKILL.md
index 367a8cc4e..56f6fdc3f 100644
--- a/.claude/skills/release/SKILL.md
+++ b/.claude/skills/release/SKILL.md
@@ -6,7 +6,9 @@ description: >
release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user
says "release", "cut a release", "bump version", "prepare a release", "make a
release", "ship it", "create release branch", or any variation of shipping a
- new version of pipelex.
+ new version of pipelex. The user can optionally provide changelog content
+ inline when invoking the skill (e.g. "/release Added new extract backend"),
+ which will be used as the changelog entry for this version.
---
# Pipelex Release Workflow
@@ -67,9 +69,15 @@ Add a new version entry at the top of the changelog for the release.
directly after the `# Changelog` title.
3. **Never add an `[Unreleased]` heading.** The changelog should only contain
concrete version entries.
-4. If the release has no changelog content yet, ask the user what to include
- before proceeding.
-5. The result should look like:
+4. If the user provided changelog content when invoking the skill (e.g.
+ `/release Added new extract backend`), use that content as the changelog
+ entry for this version. Format it properly under the appropriate heading
+ (e.g. `### Added`, `### Changed`, `### Fixed`), inferring the heading from
+ the content when possible.
+5. If the release has no changelog content yet (neither from an `[Unreleased]`
+ section nor from inline user input), ask the user what to include before
+ proceeding.
+6. The result should look like:
```markdown
# Changelog
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3906d2baf..bbe206b14 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,30 @@
# Changelog
+## [v0.21.0] - 2026-03-19
+
+### Added
+
+- **Web Page Extraction:** `PipeExtract` now supports extracting content from web pages via the new `linkup-fetch` model, with `render_js` and `include_raw_html` parameters. Added `@default-extract-web-page` alias to the extraction model deck.
+- **New AI Models:** OpenAI / Azure: `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.2-codex`; Mistral: `mistral-small-4`
+- **DocumentContent Enhancements:** Added `public_url`, `filename`, `title`, and `snippet` fields to support web pages and search citations.
+- **AI Agent Documentation:** Integrated `mkdocs-llmstxt-md` plugin to generate `/llms.txt` and `/llms-full.txt` for AI agents.
+- **Claude Code Skills:** Added internal `.claude/skills` (`add-model`, `test-model`) for registering and testing new inference models.
+
+### Changed
+
+- **Web Fetching → Extract Domain:** Moved web fetching from the Search domain into the Extract domain. Replaced `FetchJob`, `FetchWorkerAbstract`, and related classes with native handling in `PipeExtract` and a new `GatewayExtractWorker`. Split `LinkupWorker` into dedicated `LinkupSearchWorker` and `LinkupExtractWorker`.
+- **Search Results Unification:** `SearchResultContent` now uses `DocumentContent` instead of the removed `SearchSourceContent`.
+- **Search Job Refactoring:** Encapsulated `SearchJob` parameters into a new `SearchJobParams` object; updated `SearchWorkerAbstract` signatures accordingly.
+- **Documentation Build:** Replaced inline HTML generation with a `docs/root-index.html` template. Updated `robots.txt` to allow AI crawler access to `llms.txt`.
+
+### Fixed
+
+- **Remote Image Fetching:** Added error handling (`httpx.HTTPStatusError`, `httpx.RequestError`) in `GeneratedContentFactory` when downloading remote images, with graceful fallback to using the original URL as `public_url`.
+
+### Removed
+
+- **`page_image_captions` parameter:** Removed from `PipeExtractSpec` and `ExtractJobParams`.
+
## [v0.20.13] - 2026-03-16
### Removed
diff --git a/pyproject.toml b/pyproject.toml
index a33c719ec..172fb9445 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "pipelex"
-version = "0.20.13"
+version = "0.21.0"
description = "Execute composable AI methods declared in the MTHDS open standard"
authors = [{ name = "Evotis S.A.S.", email = "[email protected]" }]
maintainers = [{ name = "Pipelex staff", email = "[email protected]" }]
diff --git a/uv.lock b/uv.lock
index 9e0f984f7..ccc809cba 100644
--- a/uv.lock
+++ b/uv.lock
@@ -3449,7 +3449,7 @@ wheels = [
[[package]]
name = "pipelex"
-version = "0.20.13"
+version = "0.21.0"
source = { editable = "." }
dependencies = [
{ name = "aiofiles" },