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 v0.57.0

Louis Choquelcd37c169d710
diff --git a/.badges/tests.json b/.badges/tests.json
index 62a1a19e9..8d2bc1eb6 100644
--- a/.badges/tests.json
+++ b/.badges/tests.json
@@ -1,7 +1,7 @@
{
"schemaVersion": 1,
"label": "tests",
- "message": "11720",
+ "message": "11750",
"color": "blue",
"cacheSeconds": 300
}
diff --git a/.test_durations b/.test_durations
index a5a22ba2f..b7869e50d 100644
--- a/.test_durations
+++ b/.test_durations
@@ -582,6 +582,12 @@
"tests/integration/pipelex/pipeline/test_cost_report_rendering.py::TestCostReportRendering::test_no_costs_renders_nothing": 1.0058,
"tests/integration/pipelex/pipeline/test_cost_report_rendering.py::TestCostReportRendering::test_renders_correct_non_zero_totals": 0.7723,
"tests/integration/pipelex/pipeline/test_cost_report_rendering.py::TestCostReportRendering::test_renders_free_model_tokens_with_zero_cost": 0.0039,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_an_unexpected_builder_error_is_reported_and_the_run_succeeds": 0.2914,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_builder_failure_is_reported_on_the_output_and_the_run_succeeds": 1.9048,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_graph_off_carries_no_artifacts": 1.8945,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_graph_on_carries_artifacts_keyed_by_the_whole_run_library": 1.9186,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_graphspec_json_off_carries_no_artifacts": 1.9044,
+ "tests/integration/pipelex/pipeline/test_direct_pipe_io_artifacts.py::TestDirectPipeIOArtifacts::test_validate_does_not_build_the_artifacts_a_second_time": 2.0501,
"tests/integration/pipelex/pipeline/test_direct_tracing_assembly.py::TestDirectTracingAssembly::test_costs_on_populates_tokens_usages": 1.7729,
"tests/integration/pipelex/pipeline/test_direct_tracing_assembly.py::TestDirectTracingAssembly::test_costs_only_leaves_graph_spec_none": 0.8921,
"tests/integration/pipelex/pipeline/test_direct_tracing_assembly.py::TestDirectTracingAssembly::test_costs_only_skips_stuff_serialization": 1.1575,
@@ -659,6 +665,7 @@
"tests/integration/pipelex/pipeline/test_optional_method_inputs.py::TestOptionalMethodInputs::test_omitted_optional_input_records_not_provided": 1.2903,
"tests/integration/pipelex/pipeline/test_optional_method_inputs.py::TestOptionalMethodInputs::test_preexisting_absence_record_keeps_its_provenance": 0.06,
"tests/integration/pipelex/pipeline/test_optional_method_inputs.py::TestOptionalMethodInputs::test_provided_optional_input_leaves_no_record": 0.0748,
+ "tests/integration/pipelex/pipeline/test_pipe_io_artifacts.py::TestBuildPipeIOArtifacts::test_equals_the_three_builders_in_sequence_and_shares_one_key_set": 0.6938,
"tests/integration/pipelex/pipeline/test_pipe_io_contracts.py::TestBuildPipeIOContracts::test_anything_input_publishes_permissive_schema": 0.4712,
"tests/integration/pipelex/pipeline/test_pipe_io_contracts.py::TestBuildPipeIOContracts::test_multiplicity_entry_shapes": 1.4763,
"tests/integration/pipelex/pipeline/test_pipe_io_contracts.py::TestBuildPipeIOContracts::test_optional_markers_reported_on_contracts": 3.2615,
@@ -704,6 +711,7 @@
"tests/integration/pipelex/pipeline/test_resolve_bundle.py::TestResolveCrateFromContents::test_invalid_contents_raise_shared_verdict_and_tear_down": 0.0527,
"tests/integration/pipelex/pipeline/test_resolve_bundle.py::TestResolveCrateFromContents::test_multi_bundle_contents_resolve_to_normalized_crate": 1.1149,
"tests/integration/pipelex/pipeline/test_resolve_bundle.py::TestResolveCrateFromContents::test_sources_length_mismatch_is_a_host_wiring_error": 0.0003,
+ "tests/integration/pipelex/pipeline/test_run_artifacts_parity.py::TestRunArtifactsParity::test_a_run_writes_what_validate_reports": 2.6926,
"tests/integration/pipelex/pipeline/test_runner_library_lifecycle.py::TestRunnerLibraryLifecycle::test_failure_when_outer_is_run_library_clears_instead_of_dangling": 0.5088,
"tests/integration/pipelex/pipeline/test_runner_library_lifecycle.py::TestRunnerLibraryLifecycle::test_success_clears_when_no_outer_library": 1.2636,
"tests/integration/pipelex/pipeline/test_runner_library_lifecycle.py::TestRunnerLibraryLifecycle::test_success_restores_outer_current_library": 2.3609,
@@ -1763,6 +1771,8 @@
"tests/unit/pipelex/cli/agent_cli/test_run_bundle_auto_inputs.py::TestAgentRunBundleAutoInputs::test_piped_stdin_preempts_ambiguous_auto_detect": 0.0083,
"tests/unit/pipelex/cli/agent_cli/test_run_core_absent_output.py::TestAgentRunCoreAbsentOutput::test_absent_main_output_returns_absence_payload": 0.8161,
"tests/unit/pipelex/cli/agent_cli/test_run_core_absent_output.py::TestAgentRunCoreAbsentOutput::test_absent_main_output_with_memory_renders_markdown_absence_doc": 0.1058,
+ "tests/unit/pipelex/cli/agent_cli/test_run_core_graph_inclusion.py::TestAgentRunCoreGraphInclusion::test_graph_off_leaves_the_configured_inclusion_alone": 1.6704,
+ "tests/unit/pipelex/cli/agent_cli/test_run_core_graph_inclusion.py::TestAgentRunCoreGraphInclusion::test_graph_on_forces_the_graphspec_before_the_run": 0.1267,
"tests/unit/pipelex/cli/agent_cli/test_run_core_inputs_base_dir.py::TestRunCoreInputsBaseDir::test_inputs_base_dir_defaults_to_none": 0.0873,
"tests/unit/pipelex/cli/agent_cli/test_run_core_inputs_base_dir.py::TestRunCoreInputsBaseDir::test_inputs_base_dir_forwarded_to_runner": 0.9627,
"tests/unit/pipelex/cli/agent_cli/test_run_format.py::TestRunFormat::test_run_pipe_json_with_format_json": 0.1046,
@@ -5673,6 +5683,10 @@
"tests/unit/pipelex/core/pipes/test_parse_concept_with_multiplicity.py::TestParseConceptWithMultiplicity::test_valid_hierarchical_domain_concept_with_fixed_count": 0.0005,
"tests/unit/pipelex/core/pipes/test_parse_concept_with_multiplicity.py::TestParseConceptWithMultiplicity::test_valid_hierarchical_domain_concept_with_variable_list": 0.0006,
"tests/unit/pipelex/core/pipes/test_parse_concept_with_multiplicity.py::TestParseConceptWithMultiplicity::test_valid_simple_concept": 1.0196,
+ "tests/unit/pipelex/core/pipes/test_pipe_io_artifacts.py::TestPipeIOArtifactsModel::test_forbids_extra_fields": 0.2437,
+ "tests/unit/pipelex/core/pipes/test_pipe_io_artifacts.py::TestPipeIOArtifactsModel::test_round_trips_through_json_mode_dump": 1.6581,
+ "tests/unit/pipelex/core/pipes/test_pipe_io_artifacts.py::TestRenderPipeIOArtifactFiles::test_each_file_is_the_corpus_byte_discipline_over_the_json_mode_dump": 1.6665,
+ "tests/unit/pipelex/core/pipes/test_pipe_io_artifacts.py::TestRenderPipeIOArtifactFiles::test_yields_exactly_the_three_sibling_files": 0.0162,
"tests/unit/pipelex/core/pipes/test_stuff_spec.py::TestStuffSpecStructurelessRender::test_json_multiple_wraps_in_list[3]": 0.0016,
"tests/unit/pipelex/core/pipes/test_stuff_spec.py::TestStuffSpecStructurelessRender::test_json_multiple_wraps_in_list[True]": 0.0011,
"tests/unit/pipelex/core/pipes/test_stuff_spec.py::TestStuffSpecStructurelessRender::test_json_single_is_empty_mapping": 0.5727,
@@ -6537,6 +6551,14 @@
"tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphOutputGeneration::test_graphspec_json_only": 0.0008,
"tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphOutputGeneration::test_mermaid_mmd_contains_node_labels": 0.1555,
"tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphOutputGeneration::test_save_outputs_to_dir": 0.292,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_a_fresh_directory_removes_nothing_and_says_nothing": 0.0356,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_a_graphspec_without_artifacts_removes_the_previous_companions": 1.7537,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_filled_when_graphspec_json_is_on_and_artifacts_are_given": 0.2312,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_no_graphspec_leaves_the_directory_alone": 1.6886,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_none_when_graphspec_json_is_off": 1.6565,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_none_when_the_run_carried_no_artifacts": 0.0257,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_nothing_saved_without_artifacts": 0.0293,
+ "tests/unit/pipelex/graph/test_graph_output_generation.py::TestGraphspecCompanions::test_saved_beside_the_graphspec_under_the_standard_names": 1.7007,
"tests/unit/pipelex/graph/test_graph_rendering.py::TestRenderGraphFromSpec::test_format_selection_sets_correct_inclusion[False-True]": 0.0046,
"tests/unit/pipelex/graph/test_graph_rendering.py::TestRenderGraphFromSpec::test_format_selection_sets_correct_inclusion[True-False]": 1.1335,
"tests/unit/pipelex/graph/test_graph_rendering.py::TestRenderGraphFromSpec::test_format_selection_sets_correct_inclusion[True-True]": 0.0044,
@@ -6706,6 +6728,7 @@
"tests/unit/pipelex/graph/test_trace_context.py::TestTraceContext::test_copy_for_child_preserves_data_inclusion": 0.1237,
"tests/unit/pipelex/graph/test_trace_context.py::TestTraceContext::test_make_node_id": 0.9531,
"tests/unit/pipelex/graph/test_trace_context_emit_flags.py::TestTraceContextEmitFlags::test_copy_for_child_preserves_costs_only_flags": 0.0007,
+ "tests/unit/pipelex/graph/test_trace_context_emit_flags.py::TestTraceContextEmitFlags::test_copy_for_child_preserves_describe_pipe_io_off": 0.2496,
"tests/unit/pipelex/graph/test_trace_context_emit_flags.py::TestTraceContextEmitFlags::test_copy_for_child_preserves_graph_only_flags": 0.1706,
"tests/unit/pipelex/graph/test_trace_context_emit_flags.py::TestTraceContextEmitFlags::test_defaults_emit_both_streams": 1.1304,
"tests/unit/pipelex/kernel/test_document_reference.py::TestDocumentReference::test_create_direct_list_reference": 0.0003,
@@ -7110,6 +7133,7 @@
"tests/unit/pipelex/libraries/test_pipe_library_lookup.py::TestPipeLibraryLookup::test_remove_pipes_by_refs": 0.0918,
"tests/unit/pipelex/libraries/test_pipe_library_lookup.py::TestPipeLibraryLookup::test_same_code_different_domains_no_collision": 0.0009,
"tests/unit/pipelex/libraries/test_pipe_library_lookup.py::TestPipeLibraryLookup::test_same_pipe_ref_collision_raises": 0.001,
+ "tests/unit/pipelex/libraries/test_pipe_library_lookup.py::TestPipeLibraryOwnPipes::test_own_pipes_exclude_dependency_entries": 1.6698,
"tests/unit/pipelex/libraries/test_standalone_reserved_domains.py::TestStandaloneReservedDomains::test_manifest_error_non_reserved_domain_passes": 0.1251,
"tests/unit/pipelex/libraries/test_standalone_reserved_domains.py::TestStandaloneReservedDomains::test_manifest_error_still_checks_reserved_domains[mthds]": 0.0599,
"tests/unit/pipelex/libraries/test_standalone_reserved_domains.py::TestStandaloneReservedDomains::test_manifest_error_still_checks_reserved_domains[native]": 0.0461,
@@ -8271,11 +8295,15 @@
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_failed_webhook_log_includes_request_id_when_set": 0.0891,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_absent_main_raw": 0.0049,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_absent_main_typed": 0.0035,
+ "tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_omits_the_companions_without_a_graph": 1.6705,
+ "tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_omits_the_companions_without_artifacts": 0.0315,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_raises_without_main_stuff_raw": 0.0023,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_raises_without_main_stuff_typed": 0.0014,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_usage_artifact_carries_assembly_error": 0.0106,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_usage_artifact_null_when_usage_off": 0.0095,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_with_pydantic_instances_in_raw": 0.0172,
+ "tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_writes_the_graphspec_companions_raw": 1.6675,
+ "tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_writes_the_graphspec_companions_typed": 0.2996,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_generate_result_files_writes_usage_artifact_with_records": 0.012,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_key_prefix_inserts_a_level_and_never_supplies_the_leaf": 0.2212,
"tests/unit/pipelex/pipe_run/test_delivery_executor.py::TestDeliveryExecutor::test_raw_fallback_html_escapes_special_chars": 0.0513,
@@ -9767,6 +9795,7 @@
"tests/unit/pipelex/runtime_bridge/test_output_serialization.py::TestSerializeCompletedOutput::test_main_stuff_name_resolves_aliased_root_key": 0.0002,
"tests/unit/pipelex/runtime_bridge/test_output_serialization.py::TestSerializeCompletedOutput::test_main_stuff_name_resolves_direct_root_key": 0.0003,
"tests/unit/pipelex/runtime_bridge/test_output_serialization.py::TestSerializeCompletedOutput::test_missing_main_stuff_raises": 0.0017,
+ "tests/unit/pipelex/runtime_bridge/test_output_serialization.py::TestSerializeCompletedOutput::test_pipe_io_artifacts_and_their_error_cross_the_bridge_boundary": 0.2662,
"tests/unit/pipelex/system/configuration/test_boot_tolerance.py::TestReplayingASurfaceInMemory::test_a_current_file_is_nothing_the_ledger_has_to_say_about": 0.8279,
"tests/unit/pipelex/system/configuration/test_boot_tolerance.py::TestReplayingASurfaceInMemory::test_a_file_that_cannot_be_parsed_abandons_the_whole_retry": 0.0188,
"tests/unit/pipelex/system/configuration/test_boot_tolerance.py::TestReplayingASurfaceInMemory::test_a_later_layer_wins_on_a_key_both_carry": 0.0071,
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 26405f647..3a92451f0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,22 +1,21 @@
# Changelog
-## [Unreleased]
+## [v0.57.0] - 2026-09-07
### Added
-- **A run's results carry the I/O artifacts that describe its data:** beside `graphspec.json`, and gated by the same `graphspec_json` inclusion flag, a run now writes `pipe_io_contracts.json`, `input_form.json` and `output_form.json`, the validation report's own artifacts under the standard's names, keyed by namespaced `pipe_ref` for every pipe of the library the run executed against (its own pipes, not a dependency package's aliased entries), which is the validated bundle plus whatever `library_dirs` loaded beside it. A graph viewer shows a data node's value only when it holds the contracts and the output form, and until now only `/validate` produced them, so every consumer of a run's graph either took the no-data floor or paired the graph with a validation of some other bundle text. They are built once at the end of the run, inside its library window, and ride on `PipeOutput.pipe_io_artifacts` beside `graph_spec` (a build failure of any kind lands on `pipe_io_artifacts_error`, never failing the run nor skipping its delivery); the SPI payload carries them as `pipe_io_artifacts_dump`, ready for the synchronous `/execute` response to relay once the API reads the field. `pipelex run`, `pipelex-agent run` (which also names the three paths in its `graph_files`, and settles its graph inclusion before the run so the companions are always built with its graphspec) and the direct-mode delivery executor all write them; a graphspec written into a reused directory removes, with a warning, an earlier run's companions when the new run carries none; a run hosted on our Temporal plugin writes `graphspec.json` without its siblings until the plugin builds them in the crate's window; the fixture corpus is unchanged, since the corpus generator now renders through the same function. See [Execution Graph Tracing](under-the-hood/execution-graph-tracing.md#outputs).
-- **The `--version` handshake reports three numbers (breaking):** `pipelex --version` and `pipelex-agent --version` now print the runtime version, the MTHDS Protocol version and the MTHDS standard version, one `<label> <version>` line each, instead of the runtime version alone. A client needs all three to know what it is talking to, and they move on independent cadences under the standard's own versioning rule, so no one of them can be inferred from another. The first line keeps its historical `<program> <version>` form, so a consumer that matches a version out of the text is unaffected — but one that treats the whole of stdout as a single version string now holds three lines, and both `mthds` runners have to be adapted. Match on the label, not on the shape of the output as a whole. The two MTHDS numbers are read from the `mthds` package rather than restated here. See [CLI Reference](tools/cli/index.md#the-version-handshake).
+- **A run's results carry the I/O artifacts that describe its data**: beside `graphspec.json`, and gated by the same `graphspec_json` inclusion flag, a run now writes `pipe_io_contracts.json`, `input_form.json` and `output_form.json` — the validation report's own artifacts under the standard's names, keyed by namespaced `pipe_ref` for every pipe of the library the run executed against. Until now only `/validate` produced them, so a consumer of a run's graph either took the no-data floor or paired the graph with a validation of some other bundle text, and a graph viewer shows a data node's value only when it holds the contracts and the output form. They ride on `PipeOutput.pipe_io_artifacts` beside `graph_spec`, with a build failure of any kind landing on `pipe_io_artifacts_error` rather than failing the run or skipping its delivery, and the SPI payload carries them as `pipe_io_artifacts_dump`. `pipelex run`, `pipelex-agent run` and the direct-mode delivery executor all write them, while a run hosted on our Temporal plugin still writes `graphspec.json` without its siblings. See [Execution Graph Tracing](under-the-hood/execution-graph-tracing.md#outputs).
+- **The `--version` handshake reports three numbers (Breaking)**: `pipelex --version` and `pipelex-agent --version` now print the runtime version, the MTHDS Protocol version and the MTHDS standard version, one `<label> <version>` line each, instead of the runtime version alone. The three move on independent cadences under the standard's own versioning rule, so none can be inferred from another, and the two MTHDS numbers are read from the `mthds` package rather than restated here. The first line keeps its historical `<program> <version>` form, so a consumer that matches a version out of the text is unaffected — but one that treats the whole of stdout as a single version string now holds three lines, so match on the label rather than on the shape of the output. See [CLI Reference](tools/cli/index.md#the-version-handshake).
### Changed
-- **The Commands section of the agent rules is a compact list, so the generated `CLAUDE.md` costs every session a third of what it did.** `pipelex/kit/agent_rules/commands.md` drops its long-form headings and code blocks for one bullet per gate, each naming the target, its alias, when to run it and where the full rationale lives; `make rules` regenerates `CLAUDE.md` from it. It also now says the one thing a session could not learn from the file itself: that `CLAUDE.md` and `AGENTS.md` are generated, that `make rules` is how they move, and that `make check-rules` is a CI gate `make agent-check` does not run. The repo's Claude Code permission allowlist pre-approves the targets the rules recommend (`atd`, `ttg`, `cko`, `sgr`, the drift and rules targets, the generator aliases), so following the rules does not prompt.
-
-- **The MTHDS standard version this runtime implements is now `2.0.0` (breaking):** `mthds` moves to `==0.14.0`, whose `MTHDS_STANDARD_VERSION` was cut from `1.0.0` to `2.0.0` — the standard's first cut under its own versioning rule, accounting for breaking changes to the native set and to the manifest, lock and resolution rules that had already shipped unversioned. Two things follow for users, and no pipelex line caused either: every normalized crate this engine emits is stamped `2.0.0` instead of `1.0.0` (crate fingerprints are unaffected — `mthds_version` is excluded from the hashed payload by design), and a `METHODS.toml` whose `mthds_version` pinned the old major, such as `^1.0.0`, now warns where it did not before. A plain floor like `>=1.0.0` is still satisfied. The protocol version is unchanged at `0.6.0`. The pin stays exact, so everyone downstream inherits `mthds==0.14.0`; a consumer depending on `mthds` directly must move in step.
+- **The MTHDS standard version this runtime implements is now `2.0.0` (Breaking)**: `mthds` moves to `==0.14.0`, whose `MTHDS_STANDARD_VERSION` was cut from `1.0.0` to `2.0.0` — the standard's first cut under its own versioning rule, accounting for breaking changes to the native set and to the manifest, lock and resolution rules that had already shipped unversioned. Two things follow for users, and no pipelex line caused either: every normalized crate this engine emits is stamped `2.0.0` instead of `1.0.0` (crate fingerprints are unaffected, because `mthds_version` is excluded from the hashed payload by design), and a `METHODS.toml` whose `mthds_version` pinned the old major, such as `^1.0.0`, now warns where it did not before, while a plain floor like `>=1.0.0` is still satisfied. The protocol version is unchanged at `0.6.0`, and the pin stays exact, so a consumer depending on `mthds` directly must move in step.
+- **The Commands section of the shipped agent rules is a compact list**: `pipelex/kit/agent_rules/commands.md` drops its long-form headings and code blocks for one bullet per gate — the target, its alias, when to run it and where the full rationale lives — so the `CLAUDE.md` that `make rules` generates from it costs a session a third of what it did. It also now records the one thing a session could not learn from the file itself: that `CLAUDE.md` and `AGENTS.md` are generated, that `make rules` is how they move, and that `make check-rules` is a CI gate `make agent-check` does not run.
### Fixed
-- **The codegen stamp reference no longer understates what moves a fingerprint:** [Codegen Projections](under-the-hood/codegen-projections.md) said a stamp moves only when a method's effective type surface changes, which would have a reader mistake an ordinary restamp for drift and expect a prompt edit to leave the generated tree alone. The crate fingerprint is computed over the whole normalized crate — concepts, pipes and domains — so an edited `system_prompt` or a swapped model restamps every generated file exactly as a renamed concept field does, with the body below the fence byte-identical. `content_hash`, in the stamp header and in the lock's `artifacts[]` entries, is what distinguishes that harmless restamp from a real change to the generated code. The `pipelex/codegen/stamp.py` module docstring carried the same understatement and was corrected with it.
-- **Compound version constraints written the documented way now parse:** `parse_constraint` stripped no whitespace around the comma that ANDs a compound constraint's clauses, so `>=1.0.0, <2.0.0` — the exact spelling of the MTHDS standard's own example — was rejected while the identical `>=1.0.0,<2.0.0` parsed. A manifest's `mthds_version` written that way therefore got no compatibility check at all, since the load path degrades an unparseable constraint to a log line. A malformed compound such as `>=1.0.0,,<2.0.0` still fails, because normalizing whitespace must not repair a broken constraint.
+- **The codegen stamp reference no longer understates what moves a fingerprint**: [Codegen Projections](under-the-hood/codegen-projections.md) said a stamp moves only when a method's effective type surface changes, which would have a reader mistake an ordinary restamp for drift and expect a prompt edit to leave the generated tree alone. The crate fingerprint is computed over the whole normalized crate — concepts, pipes and domains — so an edited `system_prompt` or a swapped model restamps every generated file exactly as a renamed concept field does, with the body below the fence byte-identical. `content_hash`, in the stamp header and in the lock's `artifacts[]` entries, is what distinguishes that harmless restamp from a real change to the generated code.
+- **Compound version constraints written the documented way now parse**: `parse_constraint` stripped no whitespace around the comma that ANDs a compound constraint's clauses, so `>=1.0.0, <2.0.0` — the exact spelling of the MTHDS standard's own example — was rejected while the identical `>=1.0.0,<2.0.0` parsed. A manifest's `mthds_version` written that way therefore got no compatibility check at all, since the load path degrades an unparseable constraint to a log line. A malformed compound such as `>=1.0.0,,<2.0.0` still fails, because normalizing whitespace must not repair a broken constraint.
## [v0.56.0] - 2026-09-03
diff --git a/docs/errors/inference-backend-library-error.md b/docs/errors/inference-backend-library-error.md
index 2caba9abc..cdd4575df 100644
--- a/docs/errors/inference-backend-library-error.md
+++ b/docs/errors/inference-backend-library-error.md
@@ -7,6 +7,8 @@ description: "Reference for the `InferenceBackendLibraryError` Pipelex error cla
# Inference backend library
+A backend the library cannot load.
+
| Field | Value |
|---|---|
| `error_type` | `InferenceBackendLibraryError` |
diff --git a/pyproject.toml b/pyproject.toml
index d4c1d8317..fde6a5509 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "pipelex"
-version = "0.56.0"
+version = "0.57.0"
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 9cea9be83..acaa89e87 100644
--- a/uv.lock
+++ b/uv.lock
@@ -3303,7 +3303,7 @@ wheels = [
[[package]]
name = "pipelex"
-version = "0.56.0"
+version = "0.57.0"
source = { editable = "." }
dependencies = [
{ name = "aiofiles" },