feat(llm): implement Anthropic Claude and Google Gemini LLM provider backends #8619

Open
opened 2026-04-13 21:16:12 +00:00 by HAL9000 · 0 comments
Owner

Metadata

  • Commit message type: feat
  • Scope: llm
  • Branch name prefix: feat/v3.6.0-anthropic-gemini-backends

Background and Context

As part of Epic #8505 (Advanced Context Strategies & LLM Provider Extensions), at least 2 additional LLM backends must be integrated: Anthropic Claude and Google Gemini. These backends implement the LLMProvider protocol.

This issue depends on the LLMProvider abstraction being implemented first.

This issue blocks Epic #8505.

Expected Behavior

  • AnthropicProvider implements the LLMProvider protocol using the Anthropic API
  • GeminiProvider implements the LLMProvider protocol using the Google Gemini API
  • Both providers support streaming and non-streaming responses
  • Both providers handle rate limiting and retries

Acceptance Criteria

  • AnthropicProvider is implemented and functional
  • GeminiProvider is implemented and functional
  • Both providers support streaming responses
  • Both providers handle rate limiting with exponential backoff
  • Integration tests verify both providers with real API calls (or mocked)
  • Unit tests achieve >= 97% coverage

Subtasks

  • Implement AnthropicProvider using Anthropic Python SDK
  • Implement GeminiProvider using Google Generative AI SDK
  • Add streaming support to both providers
  • Add rate limiting and retry handling
  • Write integration tests for both providers
  • Write unit tests for both providers

Definition of Done

  1. Anthropic Claude and Google Gemini backends are implemented
  2. Integration tests verify both providers
  3. Unit tests pass with >= 97% coverage
  4. Code reviewed and merged to main branch

Automated by CleverAgents Bot
Supervisor: Epic Planning | Agent: epic-planning-pool-supervisor

## Metadata - **Commit message type**: `feat` - **Scope**: `llm` - **Branch name prefix**: `feat/v3.6.0-anthropic-gemini-backends` ## Background and Context As part of Epic #8505 (Advanced Context Strategies & LLM Provider Extensions), at least 2 additional LLM backends must be integrated: Anthropic Claude and Google Gemini. These backends implement the `LLMProvider` protocol. This issue depends on the LLMProvider abstraction being implemented first. This issue blocks Epic #8505. ## Expected Behavior - `AnthropicProvider` implements the `LLMProvider` protocol using the Anthropic API - `GeminiProvider` implements the `LLMProvider` protocol using the Google Gemini API - Both providers support streaming and non-streaming responses - Both providers handle rate limiting and retries ## Acceptance Criteria - [ ] `AnthropicProvider` is implemented and functional - [ ] `GeminiProvider` is implemented and functional - [ ] Both providers support streaming responses - [ ] Both providers handle rate limiting with exponential backoff - [ ] Integration tests verify both providers with real API calls (or mocked) - [ ] Unit tests achieve >= 97% coverage ## Subtasks - [ ] Implement `AnthropicProvider` using Anthropic Python SDK - [ ] Implement `GeminiProvider` using Google Generative AI SDK - [ ] Add streaming support to both providers - [ ] Add rate limiting and retry handling - [ ] Write integration tests for both providers - [ ] Write unit tests for both providers ## Definition of Done 1. Anthropic Claude and Google Gemini backends are implemented 2. Integration tests verify both providers 3. Unit tests pass with >= 97% coverage 4. Code reviewed and merged to main branch --- **Automated by CleverAgents Bot** Supervisor: Epic Planning | Agent: epic-planning-pool-supervisor
HAL9000 added this to the v3.6.0 milestone 2026-04-13 21:16:33 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
cleveragents/cleveragents-core#8619
No description provided.