1.52.0

New Features

• Add claude-opus-4-7 to the set of models recognized as having a 1M token context window.
• Add claude-opus-4-7 and claude-opus-4-1 to the cost tracking table.
• Adds an authenticated field to the /info endpoint that is true if the test agent is configured with a valid Datadog API key and site.

Bug Fixes

• claude hooks: context_delta is now correctly reported on agent spans in instrumented Claude Code sessions that nest llm spans within step spans.
• Fix Claude Code cost tracking to use the reduced Anthropic pricing for Claude Opus 4.5 / 4.6 / 4.7 ($5 / $25 / $0.50 cache-read / $6.25 cache-write per Mtok). Previously these models were priced at the legacy Opus 4 rates, overestimating cost by exactly 3x. Opus 4 / 4.1 / 3 continue to use the legacy higher rates, and an explicit claude-opus-4-5 entry has been added so it no longer falls through to the claude-opus-4 prefix.
• Pi hooks LLM spans previously had an empty input.messages list, losing the user prompt and never recording the system prompt. The pi lapdog extension now captures the system prompt from before_agent_start and snapshots the messages array from each context event, forwarding both with message_start so each LLM span records the system, user, assistant, and toolResult messages sent to the model.