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 v0.72.0
Louis Choqueld3b2ccb6ae56
diff --git a/.badges/tests.json b/.badges/tests.jsonindex 460049f45..ce4e077c1 100644--- a/.badges/tests.json+++ b/.badges/tests.json@@ -1,7 +1,7 @@{"schemaVersion": 1,"label": "tests",- "message": "14025",+ "message": "15396","color": "blue","cacheSeconds": 300}diff --git a/CHANGELOG.md b/CHANGELOG.mdindex e1c3b47cb..cdfc1869f 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -1,12 +1,11 @@# Changelog-## [Unreleased]+## [v0.72.0] - 2026-10-04### Added- **`PipeJudge`, an operator asking a judgment model one closed question about its inputs**: a step declaring neither `options` nor `levels` asks a yes/no question, which may carry `criteria` and a `threshold`, and outputs a `YesNo`; one declaring `options` outputs a `Choice`; one declaring `levels` outputs a `Rating`, each verdict carrying the probabilities the model measured. Every declared input is sent to the model as material whether or not the `question` reads it, and `prompt` is read as a synonym of `question`. A step is refused when the method loads if it names no model while the deck names no default for judgments, if its output disagrees with its kind of question (`Dynamic` included), if an input name reaches into a field with a dot, or if it has an image or a document input its model does not read, and a document a run is given in a format its model does not read is refused before the run starts. The builder and `pipelex-agent pipe` write it with `question`, and the MTHDS Test Corpus gains `operator_judge_urgent_message` and the `operator.judge` tag.-- **The judgment family carries files**: `JudgmentJob` and `JudgmentAssignment` carry `images` and `documents` keyed by input name, a scoped run's read authorization sees them, and a judgment worker refuses files its model does not read with the new `JudgmentCapabilityError` before calling the provider. The per-file format checks a model's files go through moved to `pipelex/cogt/inference/prompt_file_checks.py`, which the LLM family now shares.-- **A `judgment` inference family**: a new family beside `llm`, `img_gen`, `extract`, `search` and `doc_gen`, for models that answer a closed-form question over some material — yes or no, one option out of a declared set, or a position on a declared scale — and report how sure they are. The worker contract is batch-shaped (one state, a map of questions, a map of answers), every measure of uncertainty is optional so a backend that measures none can still serve the family honestly, and usage is reported as real input and output tokens priced per million. The deck gains a `[judgment]` section in a new managed file, `6_judgment_deck.toml`, which `pipelex update` installs, and a deck installed before it keeps loading with no judgment model; it ships with no `choice_default`, because the family's models come with your own key and a default the Pipelex Gateway does not serve would fail every boot, so a judgment names its own model. `pipelex-agent models` lists the new category, and so does the MTHDS protocol's model list, `GET /v1/models` on the API server, where a judgment preset is an entry typed `judgment` and `?type=judgment` filters on it; a `judgment` pytest marker joins the inference markers.+- **A `judgment` inference family**: a new family beside `llm`, `img_gen`, `extract`, `search` and `doc_gen`, for models that answer a closed-form question over some material — yes or no, one option out of a declared set, or a position on a declared scale — and report how sure they are. The worker contract is batch-shaped (one state, a map of questions, a map of answers), every measure of uncertainty is optional so a backend that measures none can still serve the family honestly, and usage is reported as real input and output tokens priced per million. A `JudgmentJob` and its `JudgmentAssignment` carry `images` and `documents` keyed by input name, which a scoped run's read authorization sees, and a judgment worker refuses files its model does not read with `JudgmentCapabilityError` before calling the provider. The deck gains a `[judgment]` section in a new managed file, `6_judgment_deck.toml`, which `pipelex update` installs, and a deck installed before it keeps loading with no judgment model; it ships with no `choice_default`, because the family's models come with your own key and a default the Pipelex Gateway does not serve would fail every boot, so a judgment names its own model. `pipelex-agent models` lists the new category, and so does the MTHDS protocol's model list, `GET /v1/models` on the API server, where a judgment preset is an entry typed `judgment` and `?type=judgment` filters on it; a `judgment` pytest marker joins the inference markers.- **TypeSafe, the judgment family's first backend**: a built-in `typesafe` plugin, installed with the new `pipelex[typesafe]` extra, serves the family from TypeSafe's System One API and is reachable as `@default-judgment`, pinned to the versioned model `jev-1.13.0`. Set `TYPESAFE_API_KEY` to use it: the default routing profile sends `jev-*` models to the backend whenever it is enabled, because the Pipelex Gateway does not serve them. A rating scale longer than ten levels is refused by this backend before any request is made, and a response answered by a model other than the pinned one is reported as a warning.- **Log sink settings can name secrets**: the values of `headers` under `[runtime.log.otlp]` and `credentials_file_path` under `[runtime.log.gcp]` accept the `${…}` placeholders the inference backends use, resolved through the configured secrets provider, so a collector's token is written `"Bearer ${OTLP_AUTH_TOKEN}"` and the key path `"${GCP_CREDENTIALS_FILE_PATH}"`. The configuration keeps the placeholders, and one that does not resolve stops the boot with `LogSinkVariableError` naming the section, the key and the variable. A header value that holds a line break once resolved, as a secret read from a file often does, stops the boot with `LogSinkHeaderValueError` rather than installing an exporter that refuses every batch. `pipelex doctor` gains a Secrets Provider row, `checks.secrets_provider` in `pipelex-agent doctor`.diff --git a/docs/api-server/openapi/pipelex-api.openapi.yaml b/docs/api-server/openapi/pipelex-api.openapi.yamlindex 576d3938f..6d4ef0caf 100644--- a/docs/api-server/openapi/pipelex-api.openapi.yaml+++ b/docs/api-server/openapi/pipelex-api.openapi.yaml@@ -11,7 +11,7 @@ info:license:name: Elastic License 2.0identifier: Elastic-2.0- version: 0.71.1+ version: 0.72.0paths:/health:get:diff --git a/pyproject.toml b/pyproject.tomlindex 79816e1ed..9e9cdb3b9 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[project]name = "pipelex"-version = "0.71.1"+version = "0.72.0"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.lockindex 8d0c08afe..8d43e88ae 100644--- a/uv.lock+++ b/uv.lock@@ -3530,7 +3530,7 @@ wheels = [[[package]]name = "pipelex"-version = "0.71.1"+version = "0.72.0"source = { editable = "." }dependencies = [{ name = "aiofiles" },