agentjido / req_llm

53%

main: 53%

LAST BUILD ON BRANCH fix/google-cached-tokens

branch: fix/google-cached-tokens

CHANGE BRANCH

x

Reset

Sync Branches

• fix/google-cached-tokens
• add-bedrock-fixtures
• add-bedrock-structured-output
• add-hex-changelog-and-module-grouping
• add-json-schema-validation
• add-vertex-guide-to-docs
• add-vllm-provider
• add-vllm-support
• add_openai_responses_api_structured_responses
• add_retry_step
• allow_json_schemas
• bedrock-1.0-fixes
• bedrock-clean
• bedrock-mistral-support
• breaking/reqllm-llmdb-forced
• bug/api-return-types
• bug/codec-tool-calls
• bug/debug-stream-return
• bug/incorrect-model-spec-docs
• bug/object-array
• bug/openai-tool-calls
• bug/stream-process-linking
• bug/streaming-nil-deltas
• bug/streaming-race-condition
• bug/usage_total_cost
• cerebras
• cerebras-zai-glm-4-6
• chore/2025-10-14-update-fixtures
• chore/docs-review
• chore/model_update_2025-10-27
• chore/object-fixtures
• chore/object-fixtures-resurrected
• chore/refine-fixtures
• chore/refresh-coverage-tests
• chore/refresh-fixtures-before-1.0
• chore/update-models-2025-09-21
• config_base_url_override
• copilot/fix-32
• credo-config
• credo/code-readability-fix
• credo/fix-refactor-enum-filter
• dependabot/hex/ex_aws_auth-1.3.1
• dependabot/hex/ex_doc-0.39.1
• dependabot/hex/req-0.5.16
• dependabot/hex/tidewave-0.5.1
• dependabot/hex/zoi-0.8.1
• dependabot/hex/zoi-0.8.4
• devtools
• docs/aws-event-stream-specialization
• egomes/fix-claude-multi-turn
• egomes/fix-tool-inspection-with-json-schema
• feat/context-json-serialization
• feat/fixture-credential-fallback
• feat/google-context-caching
• feat/google-upload-file
• feat/in-type-support
• feat/oauth2-token-cache
• feat/structured-output-openai-google
• feature/base-url-override
• feature/bedrock-prompt-caching
• feature/cerebras-provider
• feature/configurable-metadata-timeout
• feature/custom_providers
• feature/google_grounding
• feature/model-catalog
• feature/normalize-bedrock-inference-profiles
• feature/pre-release-fixes
• feature/prompt-caching
• feature/refactor-llm-api-fixtures
• feature/refined-key-management
• feature/stream-collectors
• feature/unique-model-provider-options
• feature/upgrade-ex-aws-auth
• feature/zai-fixtures
• feature/zoi-schema
• fix-anthropic-streaming
• fix-bedrock-timeout
• fix-duplicate-clause
• fix-google
• fix-groq-stream-error
• fix-mix-task-docs
• fix-openai-max-tokens-param
• fix-retry-delay-conflict
• fix-schema-boolean-property
• fix/bedrock-claude-exclusions
• fix/bedrock-inference-profiles
• fix/bug-119-aws-auth-credentials
• fix/cost-calculation-in-usage
• fix/google-file-support
• fix/google-structured-output
• fix/groq-utf8-streaming
• fix/http2-large-request-bodies
• fix/issue-65-http-status-validation
• fix/issue-96-validation-error-fields
• fix/jsv-preserve-original-data
• fix/proxy-options
• fix/registry-get-provider-nil-module
• fix/tool_calls
• fix/vertex-decode-stream-event
• google-vision
• idempotent-stream-response
• improve-metadata-provider-errors
• list_with_subtype
• main
• patch-1
• put-max-tokens-model-options
• refactor-meta-provider-generic
• refactor/context-tools
• refactor/rename-decode-sse-event
• refactor/req-streaming
• refactor/xai-structured-objects
• remove-jido-keys
• vertex-gemini-rebased
• zai

Build # 7177c7cf8704fb09797422dd712c269426699916-PR-192

Build Type

Pull #192

github

Committed by neilberkman

Commit Message

Fix: Extract cached token counts from Google API responses

Fixes #191

Google's API returns cachedContentTokenCount in usageMetadata for both
implicit (automatic) and explicit (CachedContent API) prompt caching.
The provider was not extracting this field, causing cached_tokens to
always be 0 even when caching was active.

Changes:
- Extract cachedContentTokenCount from Google responses
- Convert to OpenAI-compatible prompt_tokens_details.cached_tokens format
- Affects both google and google-vertex providers using Gemini models

Pull Request Pull Request #192: Fix: Extract cached token counts from Google API responses

Run Details

5 of 6 new or added lines in 1 file covered. (83.33%)

3999 of 7570 relevant lines covered (52.83%)

353.32 hits per line