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 v0.79.1

Louis Choquel337dff2d9464
diff --git a/.badges/tests.json b/.badges/tests.json
index e946e57ba..6b1286fd2 100644
--- a/.badges/tests.json
+++ b/.badges/tests.json
@@ -1,7 +1,7 @@
{
"schemaVersion": 1,
"label": "tests",
- "message": "16551",
+ "message": "16568",
"color": "blue",
"cacheSeconds": 300
}
diff --git a/.test_durations b/.test_durations
index b76e6aef5..a287cd80c 100644
--- a/.test_durations
+++ b/.test_durations
@@ -4694,6 +4694,18 @@
"tests/unit/pipelex/cogt/inference/test_model_not_allowed.py::TestTheCodeSurvivesEveryExtractHop::test_the_refusal_through_every_hop[openai-substrate]": 0.0129,
"tests/unit/pipelex/cogt/inference/test_model_not_allowed.py::TestTheCodeSurvivesEveryExtractHop::test_the_refusal_through_every_hop[portkey-substrate]": 0.0075,
"tests/unit/pipelex/cogt/inference/test_model_not_allowed.py::TestWhatItAnswersOverHTTP::test_it_answers_500_as_an_unrecognized_412_does": 0.0004,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[absent]": 0.3059,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[date_in_the_past]": 0.0007,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[fractional_seconds]": 0.2843,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[infinity]": 0.2852,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[integer_seconds]": 0.2826,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[negative]": 0.0007,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[negative_infinity]": 0.2808,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[neither_number_nor_date]": 0.4126,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[not_a_number]": 0.0006,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[number_not_string]": 0.305,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[overflows_to_infinity]": 0.299,
+ "tests/unit/pipelex/cogt/inference/test_parse_retry_after_seconds.py::TestParseRetryAfterSeconds::test_reads_only_a_delay_the_spec_allows[zero]": 0.3034,
"tests/unit/pipelex/cogt/inference/test_provider_classification_parity.py::TestProviderClassificationParity::test_every_provider_name_has_an_extract_fn": 0.8455,
"tests/unit/pipelex/cogt/inference/test_provider_classification_parity.py::TestProviderClassificationParity::test_extract_fn_populates_envelope_for_each_provider[anthropic]": 0.002,
"tests/unit/pipelex/cogt/inference/test_provider_classification_parity.py::TestProviderClassificationParity::test_extract_fn_populates_envelope_for_each_provider[azure]": 0.0005,
@@ -4739,6 +4751,10 @@
"tests/unit/pipelex/cogt/inference/test_provider_error_metadata.py::TestProviderErrorMetadata::test_round_trips_via_model_dump_and_validate": 0.0002,
"tests/unit/pipelex/cogt/inference/test_provider_error_metadata.py::TestProviderErrorMetadata::test_sdk_exception_type_is_required": 0.0003,
"tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_content_policy_detail_when_violation_present": 0.0006,
+ "tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_failed_run_report_says_to_wait_then_run_again[no_retry_after]": 0.3098,
+ "tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_failed_run_report_says_to_wait_then_run_again[retry_after]": 0.0009,
+ "tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_failed_run_report_says_to_wait_then_run_again[retry_after_rounded_up]": 0.3211,
+ "tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_failed_run_report_says_to_wait_then_run_again[retry_after_zero]": 0.0011,
"tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_renders_failure_class_per_family[extract-extract-ExtractJobFailureError-ExtractModelNotFoundError]": 0.0012,
"tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_renders_failure_class_per_family[img_gen-img_gen-ImgGenGenerationError-ImgGenModelNotFoundError]": 0.001,
"tests/unit/pipelex/cogt/inference/test_render_inference_error.py::TestRenderInferenceError::test_renders_failure_class_per_family[llm-llm-LLMCompletionError-LLMModelNotFoundError]": 0.7963,
@@ -12078,6 +12094,7 @@
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_permission_denied_quota_is_capacity": 0.0914,
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_rate_limit[billing_limit-You have reached your billing limit-capacity-billing]": 0.0698,
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_rate_limit[generic_rate_limit-rate_limit_error: Number of request tokens has exceeded your per-minute limit-transient-retry]": 0.8694,
+ "tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_rate_limit[generic_rate_limit-rate_limit_error: Number of request tokens has exceeded your per-minute limit-transient-run it again]": 0.3219,
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_rate_limit[quota_exhaustion-Your account quota has been exceeded-capacity-billing]": 0.104,
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_server_error_is_transient": 0.1078,
"tests/unit/pipelex/providers/anthropic/test_anthropic_worker_error_handling.py::TestAnthropicWorkerErrorHandling::test_timeout_is_transient": 0.1084,
@@ -12165,6 +12182,7 @@
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[service_quota_exceeded-ServiceQuotaExceededException-You have exceeded the service quota for this resource-capacity-billing]": 0.0466,
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[service_unavailable-ServiceUnavailableException-Service is temporarily unavailable-transient-None]": 0.098,
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[throttling_generic-ThrottlingException-Rate exceeded for model-transient-retry]": 1.0364,
+ "tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[throttling_generic-ThrottlingException-Rate exceeded for model-transient-run it again]": 0.1441,
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[throttling_quota-ThrottlingException-Account quota limit exceeded for this model-capacity-billing]": 0.0959,
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_client_error_classification[validation_exception-ValidationException-Invalid parameter: max_tokens must be positive-content-None]": 0.0638,
"tests/unit/pipelex/providers/bedrock/test_bedrock_worker_error_handling.py::TestBedrockWorkerErrorHandling::test_error_report_capacity_not_retryable": 0.0587,
@@ -12365,6 +12383,7 @@
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_client_error[other_client_error_fallback-422-Unprocessable entity-configuration-review]": 0.0023,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_client_error[rate_limit_429_billing-429-Billing account is not active-capacity-billing]": 0.0044,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_client_error[rate_limit_429_generic-429-Too many requests, please slow down-transient-retry]": 0.0039,
+ "tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_client_error[rate_limit_429_generic-429-Too many requests, please slow down-transient-run it again]": 0.006,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_client_error[rate_limit_429_quota-429-Resource has been exhausted (e.g. check quota)-capacity-billing]": 0.0035,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_not_found_raises_img_gen_model_not_found_error": 0.0042,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_img_gen_server_error_has_transient_category": 0.0021,
@@ -12376,6 +12395,7 @@
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_client_error[other_client_error_fallback-422-Unprocessable entity-configuration-review]": 0.0037,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_client_error[rate_limit_429_billing-429-Billing account is not active-capacity-billing]": 0.0204,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_client_error[rate_limit_429_generic-429-Too many requests, please slow down-transient-retry]": 0.0034,
+ "tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_client_error[rate_limit_429_generic-429-Too many requests, please slow down-transient-run it again]": 0.4129,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_client_error[rate_limit_429_quota-429-Resource has been exhausted (e.g. check quota)-capacity-billing]": 0.005,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_not_found_raises_llm_model_not_found_error": 0.0019,
"tests/unit/pipelex/providers/google/test_google_worker_error_handling.py::TestGoogleWorkerErrorHandling::test_llm_server_error_has_transient_category": 0.0033,
@@ -12594,6 +12614,7 @@
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[bad_request_generic_400-400-Invalid parameter: unsupported document format-content-None]": 0.0019,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[payment_required_402-402-Payment required: insufficient credits-capacity-billing]": 0.0044,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[rate_limit_generic_429-429-Rate limit exceeded. Please retry after 20s-transient-retry]": 0.0047,
+ "tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[rate_limit_generic_429-429-Rate limit exceeded. Please retry after 20s-transient-run it again]": 0.2943,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[rate_limit_quota_429-429-Rate limit reached: your account quota has been exceeded-capacity-billing]": 0.0018,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_error_classification[server_error_503-503-Service temporarily unavailable-transient-None]": 0.0037,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_extract_worker_not_found_raises_extract_model_not_found_error": 0.0025,
@@ -12606,8 +12627,12 @@
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[forbidden_403-403-You do not have access to this resource-configuration-None]": 0.0027,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[payment_required_402-402-Payment required: insufficient credits-capacity-billing]": 0.7735,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[rate_limit_generic_429-429-Rate limit exceeded. Please retry after 20s-transient-retry]": 0.0041,
+ "tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[rate_limit_generic_429-429-Rate limit exceeded. Please retry after 20s-transient-run it again]": 0.3244,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[rate_limit_quota_429-429-Rate limit reached: your account quota has been exceeded-capacity-billing]": 0.0092,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_error_classification[server_error_500-500-Internal server error-transient-None]": 0.0032,
+ "tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_malformed_response_is_transient[choice_without_message]": 0.0045,
+ "tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_malformed_response_is_transient[no_choices]": 0.3103,
+ "tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_malformed_response_is_transient[no_response]": 0.0083,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_not_found_raises_llm_model_not_found_error": 0.0034,
"tests/unit/pipelex/providers/mistral/test_mistral_worker_error_handling.py::TestMistralWorkerErrorHandling::test_llm_worker_unhandled_4xx_is_configuration": 0.0024,
"tests/unit/pipelex/providers/openai/test_extract_openai_metadata.py::TestExtractOpenAIMetadata::test_authentication_error_carries_status_code_401": 0.0121,
@@ -12738,6 +12763,7 @@
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_connection_error_has_transient_category": 0.0883,
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_not_found_has_configuration_category": 0.0029,
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_rate_limit[generic_rate_limit-Rate limit exceeded. Please retry after 20s-transient-retry]": 0.8594,
+ "tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_rate_limit[generic_rate_limit-Rate limit exceeded. Please retry after 20s-transient-run it again]": 0.1417,
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_rate_limit[quota_exceeded-You exceeded your current quota, please check your plan-capacity-billing]": 0.0037,
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_rate_limit[quota_insufficient-Error: insufficient_quota - you have exceeded your billing limit-capacity-billing]": 0.0068,
"tests/unit/pipelex/providers/openai/test_openai_worker_error_handling.py::TestOpenAIWorkerErrorHandling::test_completions_llm_timeout[api_timeout-Request timed out-transient]": 0.0031,
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4f38aee9c..e3a0ad08b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [v0.79.1] - 2026-10-09
### Fixed
diff --git a/docs/api-server/openapi/pipelex-api.openapi.yaml b/docs/api-server/openapi/pipelex-api.openapi.yaml
index 699c80096..30414fd6f 100644
--- a/docs/api-server/openapi/pipelex-api.openapi.yaml
+++ b/docs/api-server/openapi/pipelex-api.openapi.yaml
@@ -12,7 +12,7 @@ info:
license:
name: Elastic License 2.0
identifier: Elastic-2.0
- version: 0.79.0
+ version: 0.79.1
paths:
/health:
get:
diff --git a/pyproject.toml b/pyproject.toml
index 14290824c..b32ee99ff 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "pipelex"
-version = "0.79.0"
+version = "0.79.1"
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 3f4c17733..cd53efb0c 100644
--- a/uv.lock
+++ b/uv.lock
@@ -3530,7 +3530,7 @@ wheels = [
[[package]]
name = "pipelex"
-version = "0.79.0"
+version = "0.79.1"
source = { editable = "." }
dependencies = [
{ name = "aiofiles" },