agentjido / req_llm

62%

main: 51%

LAST BUILD ON BRANCH bug/openai-tool-calls

branch: bug/openai-tool-calls

CHANGE BRANCH

x

Reset

Sync Branches

• bug/openai-tool-calls
• add-hex-changelog-and-module-grouping
• add-vllm-provider
• add_openai_responses_api_structured_responses
• allow_json_schemas
• bedrock-clean
• bug/api-return-types
• bug/codec-tool-calls
• bug/debug-stream-return
• bug/incorrect-model-spec-docs
• bug/streaming-race-condition
• cerebras
• chore/2025-10-14-update-fixtures
• chore/object-fixtures
• chore/object-fixtures-resurrected
• chore/refine-fixtures
• chore/refresh-coverage-tests
• chore/update-models-2025-09-21
• copilot/fix-32
• devtools
• egomes/fix-claude-multi-turn
• feat/context-json-serialization
• feat/google-upload-file
• feat/in-type-support
• feat/structured-output-openai-google
• feature/cerebras-provider
• feature/configurable-metadata-timeout
• feature/model-catalog
• feature/normalize-bedrock-inference-profiles
• feature/pre-release-fixes
• feature/refactor-llm-api-fixtures
• feature/refined-key-management
• feature/unique-model-provider-options
• feature/upgrade-ex-aws-auth
• feature/zai-fixtures
• fix-anthropic-streaming
• fix-duplicate-clause
• fix-google
• fix-groq-stream-error
• fix-mix-task-docs
• fix-openai-max-tokens-param
• fix/bug-119-aws-auth-credentials
• fix/cost-calculation-in-usage
• fix/google-file-support
• fix/google-structured-output
• fix/http2-large-request-bodies
• fix/issue-65-http-status-validation
• fix/issue-96-validation-error-fields
• fix/proxy-options
• fix/registry-get-provider-nil-module
• fix/tool_calls
• google-vision
• improve-metadata-provider-errors
• main
• patch-1
• put-max-tokens-model-options
• refactor/context-tools
• refactor/req-streaming
• refactor/xai-structured-objects
• remove-jido-keys
• zai

Build # b609b98275878fa032903148b26198afa35f073a-PR-59

Build Type

Pull #59

github

Committed by mikehostetler

Commit Message

Fix tool calling encoding for OpenAI provider

- Implement role-specific message encoding in Provider.Defaults
- Extract tool calls from ContentParts to top-level tool_calls field
- Normalize function arguments to JSON strings as required by OpenAI
- Add proper tool_call_id handling for tool role messages
- Update test framework with assert_tool_calling_response helper
- Add comprehensive tests for all tool calling scenarios
- Regenerate fixtures with corrected encoding behavior

Fixes #44

Amp-Thread-ID: https://ampcode.com/threads/T-3eaeee9f-d4ba-43ec-b9a8-0c823a825576
Co-authored-by: Amp <amp@ampcode.com>

Pull Request Pull Request #59: Fix tool calling encoding for OpenAI provider

Run Details

35 of 46 new or added lines in 2 files covered. (76.09%)

1745 of 2829 relevant lines covered (61.68%)

326.45 hits per line