Skip to content

:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

fix(aio): accept report_id on llma-evaluation-report-run-list (#129082)

Bernat Torresb1980daae6c7
diff --git a/products/ai_observability/mcp/tools.yaml b/products/ai_observability/mcp/tools.yaml
index 37aaa3206084..44ebda4ec7dd 100644
--- a/products/ai_observability/mcp/tools.yaml
+++ b/products/ai_observability/mcp/tools.yaml
@@ -817,9 +817,15 @@ tools:
idempotent: true
title: List evaluation report runs
description: >
- List the run history for a specific evaluation report config. Each run record includes the generated report
- content, the evaluation period covered, delivery status ('pending', 'delivered', 'failed'), and any delivery
- error details.
+ List the run history for a specific evaluation report config. `id` is the report config's UUID, not the
+ evaluation's: to find it from an evaluation, call llma-evaluation-report-list with the evaluation's UUID in
+ `evaluation`. Each run record includes the generated report content, the evaluation period covered, delivery
+ status ('pending', 'delivered', 'failed'), and any delivery error details.
+ param_overrides:
+ id:
+ aliases:
+ - report_id
+ - reportId
llma-evaluation-report-update:
operation: llm_analytics_evaluation_reports_partial_update
enabled: true
diff --git a/services/mcp/schema/generated-tool-definitions.json b/services/mcp/schema/generated-tool-definitions.json
index b0760884109b..d7e16497372d 100644
--- a/services/mcp/schema/generated-tool-definitions.json
+++ b/services/mcp/schema/generated-tool-definitions.json
@@ -9298,7 +9298,7 @@
}
},
"llma-evaluation-report-run-list": {
- "description": "List the run history for a specific evaluation report config. Each run record includes the generated report content, the evaluation period covered, delivery status ('pending', 'delivered', 'failed'), and any delivery error details.",
+ "description": "List the run history for a specific evaluation report config. `id` is the report config's UUID, not the evaluation's: to find it from an evaluation, call llma-evaluation-report-list with the evaluation's UUID in `evaluation`. Each run record includes the generated report content, the evaluation period covered, delivery status ('pending', 'delivered', 'failed'), and any delivery error details.",
"category": "AI observability",
"feature": "llm_analytics",
"summary": "List evaluation report runs",
diff --git a/services/mcp/schema/tool-definitions-all.json b/services/mcp/schema/tool-definitions-all.json
index febbc2ba34d9..089457aad4a1 100644
--- a/services/mcp/schema/tool-definitions-all.json
+++ b/services/mcp/schema/tool-definitions-all.json
@@ -9564,7 +9564,7 @@
}
},
"llma-evaluation-report-run-list": {
- "description": "List the run history for a specific evaluation report config. Each run record includes the generated report content, the evaluation period covered, delivery status ('pending', 'delivered', 'failed'), and any delivery error details.",
+ "description": "List the run history for a specific evaluation report config. `id` is the report config's UUID, not the evaluation's: to find it from an evaluation, call llma-evaluation-report-list with the evaluation's UUID in `evaluation`. Each run record includes the generated report content, the evaluation period covered, delivery status ('pending', 'delivered', 'failed'), and any delivery error details.",
"category": "AI observability",
"feature": "llm_analytics",
"summary": "List evaluation report runs",
diff --git a/services/mcp/src/tools/generated/ai_observability.ts b/services/mcp/src/tools/generated/ai_observability.ts
index 1d0ed7c8d70f..263b47bb4c05 100644
--- a/services/mcp/src/tools/generated/ai_observability.ts
+++ b/services/mcp/src/tools/generated/ai_observability.ts
@@ -1324,8 +1324,11 @@ const LlmaEvaluationReportRunListSchema = () => {
const LlmAnalyticsEvaluationReportsRunsListParams = orvalSchemas.LlmAnalyticsEvaluationReportsRunsListParams()
const LlmAnalyticsEvaluationReportsRunsListQueryParams =
orvalSchemas.LlmAnalyticsEvaluationReportsRunsListQueryParams()
- return LlmAnalyticsEvaluationReportsRunsListParams.omit({ project_id: true }).extend(
- LlmAnalyticsEvaluationReportsRunsListQueryParams.shape
+ return z.preprocess(
+ normalizeParamAliases({ id: ['report_id', 'reportId'] }),
+ LlmAnalyticsEvaluationReportsRunsListParams.omit({ project_id: true }).extend(
+ LlmAnalyticsEvaluationReportsRunsListQueryParams.shape
+ )
)
}