Add ClickHouse ingestion for autorevert advisor verdicts (#7906)

## Summary

Sets up the S3 → ClickHouse ingestion pipeline for autorevert AI advisor
verdicts, following the same pattern as `claude_code_usage`.

## Changes

- **`clickhouse_db_schema/misc.autorevert_advisor_verdicts/schema.sql`**
— new table storing verdict, confidence, summary, causal_reasoning, plus
signal metadata (signal_key, suspect_commit, pr_number, workflow_name)
- **`aws/lambda/clickhouse-replicator-s3/lambda_function.py`** — add
`autorevert_advisor_verdicts` to `SUPPORTED_PATHS` + adapter function

## S3 path


`s3://ossci-raw-job-status/autorevert_advisor_verdicts/<repo>/<run_id>_<run_attempt>.json`

## Dependencies

- S3 bucket notification for `autorevert_advisor_verdicts/` prefix →
`clickhouse-replicator-s3` Lambda (internal infra change)
- S3 write permission for the advisor workflow's IAM role (internal
infra change)
- Workflow upload step in pytorch/pytorch (separate PR)

## Test plan

- [ ] Verify CH table creation
- [ ] Verify Lambda adapter handles the JSON format correctly
- [ ] End-to-end: workflow uploads verdict → S3 notification → Lambda →
CH table

Author: izaitsevfb

aws/lambda/clickhouse-replicator-s3/lambda_function.py

@@ -690,6 +690,25 @@ def claude_code_usage_adapter(table, bucket, key):
     general_adapter(table, bucket, key, schema, ["none"], "JSONEachRow")
 
 
+def autorevert_advisor_verdicts_adapter(table, bucket, key):
+    schema = """
+    `repo` String,
+    `run_id` Int64,
+    `run_attempt` Int32,
+    `timestamp` DateTime64(3),
+    `suspect_commit` FixedString(40),
+    `pr_number` Int64,
+    `signal_key` String,
+    `signal_source` String,
+    `workflow_name` String,
+    `verdict` String,
+    `confidence` Float32,
+    `summary` String,
+    `causal_reasoning` String
+    """
+    general_adapter(table, bucket, key, schema, ["none"], "JSONEachRow")
+
+
 SUPPORTED_PATHS = {
     "merges": "default.merges",
     "queue_times_historical": "default.queue_times_historical",
@@ -711,6 +730,7 @@ def claude_code_usage_adapter(table, bucket, key):
     "util_timeseries": "misc.oss_ci_time_series",
     "disabled_tests_historical": "misc.disabled_tests_historical",
     "claude_code_usage": "misc.claude_code_usage",
+    "autorevert_advisor_verdicts": "misc.autorevert_advisor_verdicts",
     # fbossci-cloudwatch-metrics bucket
     "ghci-related": "infra_metrics.cloudwatch_metrics",
     "test_jsons_while_running": "tests.all_test_runs",
@@ -738,6 +758,7 @@ def claude_code_usage_adapter(table, bucket, key):
     "misc.oss_ci_time_series": oss_ci_util_time_series_adapter,
     "misc.disabled_tests_historical": disabled_tests_historical_adapter,
     "misc.claude_code_usage": claude_code_usage_adapter,
+    "misc.autorevert_advisor_verdicts": autorevert_advisor_verdicts_adapter,
     "infra_metrics.cloudwatch_metrics": cloudwatch_metrics_adapter,
 }
 

clickhouse_db_schema/misc.autorevert_advisor_verdicts/schema.sql

@@ -0,0 +1,21 @@
+CREATE TABLE misc.autorevert_advisor_verdicts
+(
+    `repo` LowCardinality(String),
+    `run_id` Int64,
+    `run_attempt` Int32,
+    `timestamp` DateTime64(3),
+    `suspect_commit` FixedString(40),
+    `pr_number` Int64,
+    `signal_key` String,
+    `signal_source` LowCardinality(String),
+    `workflow_name` String,
+    `verdict` Enum8('revert' = 1, 'unsure' = 2, 'not_related' = 3, 'garbage' = 4),
+    `confidence` Float32,
+    `summary` String,
+    `causal_reasoning` String,
+    `_meta` Tuple(bucket String, key String),
+    `_inserted_at` DateTime MATERIALIZED now()
+)
+ENGINE = SharedMergeTree('/clickhouse/tables/{uuid}/{shard}', '{replica}')
+ORDER BY (repo, suspect_commit, signal_key, timestamp)
+SETTINGS index_granularity = 8192