fix: anthropic usage from API response

[milancermak]

The Anthropic API does respond with the number of tokens used. It is response.messages.usage as a Usage interfaces. This PR incorporates it to DD.

Summary by CodeRabbit

• Bug Fixes
  • Improved token usage tracking for Anthropic API calls by accurately capturing input and output token counts.

[coderabbitai]

Walkthrough

The pull request modifies the executeAnthropicCompletion method in the LLMClient class, specifically updating how token counts are handled when processing responses from the Anthropic API. The changes replace hardcoded zero values for token counts with dynamic retrieval from the API response's usage object, enabling more accurate tracking of input and output tokens.

Changes

File	Change Summary
packages/core/src/core/llm-client.ts	Updated token count calculation to use response.usage.input_tokens and response.usage.output_tokens instead of hardcoded zeros

Poem

🐰 In the realm of tokens, a rabbit's delight,
Where numbers now dance with API might
Input and output, no longer at zero
Our metrics now shine like a coding hero!
Token tracking, precise and so bright 🌟

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 33f4422 and 923f68c.

📒 Files selected for processing (1)

• packages/core/src/core/llm-client.ts (1 hunks)

🔇 Additional comments (2)

packages/core/src/core/llm-client.ts (2)

130-130: LGTM! Style improvement.

Adding a trailing comma is a good practice for cleaner git diffs when parameters are added in the future.

---

137-140: Verify type safety for usage fields.

The token usage calculation is correctly implemented, mapping Anthropic's response fields to our interface. However, we should add type safety checks in case the usage fields are undefined.

Consider adding null checks:

     usage: {
-        prompt_tokens: response.usage.input_tokens,
-        completion_tokens: response.usage.output_tokens,
-        total_tokens: response.usage.input_tokens +
-          response.usage.output_tokens,
+        prompt_tokens: response.usage?.input_tokens ?? 0,
+        completion_tokens: response.usage?.output_tokens ?? 0,
+        total_tokens: (response.usage?.input_tokens ?? 0) +
+          (response.usage?.output_tokens ?? 0),
     },

Let's verify the response type with this script:

✅ Verification successful

Null safety checks are recommended for usage fields

The codebase shows consistent use of TypeScript null-safety patterns. Since the usage fields come from an external API response, we should maintain this pattern by adding null checks with safe fallbacks:

usage: {
  prompt_tokens: response.usage?.input_tokens ?? 0,
  completion_tokens: response.usage?.output_tokens ?? 0,
  total_tokens: (response.usage?.input_tokens ?? 0) +
    (response.usage?.output_tokens ?? 0),
},

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Search for Anthropic SDK type definitions to confirm the usage field structure
rg -A 5 "interface.*Usage" || rg -A 5 "type.*Usage"

Length of output: 52

---

Script:

#!/bin/bash
# Search for response type definitions and usage
ast-grep --pattern 'interface $RESP {
  $$$
  usage: {
    $$$
  }
  $$$
}'

# Search for actual response handling
rg -B 3 -A 3 "response\.usage\." 

Length of output: 881

---

Script:

#!/bin/bash
# Check type definitions and imports in the file
rg -B 10 "class LLMClient" packages/core/src/core/llm-client.ts

# Look for existing null check patterns
rg -l "(\?\.|(\?\?)|(\|\s*undefined)|(\|\s*null))" packages/core/src/core/llm-client.ts

Length of output: 364

Finishing Touches

• 📝 Generate Docstrings (Beta)

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.