sentry-python-sdk

Malicious tool definition detected

Prompt Injection

Privilege Escalation

Resource Abuse

Supply Chain Compromise

Malicious tool definition detected

## Metric Types | Type | API | Use for | |------|-----|---------| | Counter | `metrics.count()` | Event occurrences, request counts | | Distribution | `metrics.distribution()` | Latencies, sizes — supports p50/p90/p95/p99 | | Gauge | `metrics.gauge()` | Current values (min, max, avg, sum, count — no percentiles) | ## Configuration ```python import sentry_sdk sentry_sdk.init( dsn="https://<key>@<org>.ingest.sentry.io/<project>", # No extra flag — metrics are on by default ) ``` Optional `before_s

Tool passed security scan

Malicious tool definition detected

Description: or `LiteLLMIntegration` | ## Troubleshooting | Issue | Solution | |-------|----------| | No AI spans appearing | Verify `traces_sample_rate > 0`; wrap calls in a transaction | | Prompts not captured | Set `send_default_pii=True` and verify `include_prompts=True` (default) | | LiteLLM not tracked | LiteLLM is NOT auto-enabled — add `LiteLLMIntegration` to `integrations=[]` explicitly | | Token counts missing for OpenAI streaming | Install `tiktoken>=0.3.0` and set `tiktoken_encoding_

Tool passed security scan

Tool passed security scan

Tool passed security scan