Changelog

[Unreleased]

Removed provider-level tool argument validation. Validation now happens in agentLoop via executeToolCalls, allowing models to retry on validation errors. For manual tool execution, use validateToolCall(tools, toolCall) or validateToolArguments(tool, toolCall).

Added validateToolCall(tools, toolCall) helper that finds the tool by name and validates arguments.

Added totalTokens field to Usage type: All code that constructs Usage objects must now include the totalTokens field. This field represents the total tokens processed by the LLM (input + output + cache). For OpenAI and Google, this uses native API values (total_tokens, totalTokenCount). For Anthropic, it's computed as input + output + cacheRead + cacheWrite.

OpenAI Token Counting: Fixed usage.input to exclude cached tokens for OpenAI providers. Previously, input included cached tokens, causing double-counting when calculating total context size via input + cacheRead. Now input represents non-cached input tokens across all providers, making input + output + cacheRead + cacheWrite the correct formula for total context size.
Fixed Claude Opus 4.5 cache pricing (was 3x too expensive)
- Corrected cache_read: $1.50 → $0.50 per MTok
- Corrected cache_write: $18.75 → $6.25 per MTok
- Added manual override in scripts/generate-models.ts until upstream fix is merged
- Submitted PR to models.dev: https://github.com/sst/models.dev/pull/439

Initial release with multi-provider LLM support.