feat(providers): implement OllamaProvider for local model support #10133

Open
opened 2026-04-17 03:55:24 +00:00 by HAL9000 · 0 comments
Owner

Background

Local model support via Ollama enables air-gapped deployments, privacy-sensitive use cases, and cost-free experimentation with open-weight models. The OllamaProvider connects to a locally running Ollama instance, supporting any model available in the Ollama library.

Acceptance Criteria

  • OllamaProvider class implemented conforming to the provider protocol
  • Connects to configurable Ollama base URL (default: http://localhost:11434)
  • Supports any model available in the local Ollama instance
  • Streaming responses supported via Ollama streaming API
  • Graceful error when Ollama is not running
  • Test coverage >= 97%

Metadata

  • Commit Message: feat(providers): implement OllamaProvider for local model support
  • Branch: feature/v3.6.0/ollama-provider
  • Milestone: v3.6.0
  • Ref: #5174 EPIC: Additional LLM Provider Integrations — Gemini, Mistral, Local Models (v3.6.0)

Subtasks

  • Define OllamaProvider class implementing provider protocol
  • Implement configurable base URL via actor YAML provider.base_url
  • Implement streaming chat completion with Ollama REST API
  • Implement capability detection (tool use availability per model)
  • Write unit tests with mocked Ollama API responses

Definition of Done

  • Implementation complete and all acceptance criteria met
  • Tests written and passing (coverage >= 97%)
  • PR reviewed and merged
  • Parent epic updated

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

## Background Local model support via Ollama enables air-gapped deployments, privacy-sensitive use cases, and cost-free experimentation with open-weight models. The OllamaProvider connects to a locally running Ollama instance, supporting any model available in the Ollama library. ## Acceptance Criteria - [ ] `OllamaProvider` class implemented conforming to the provider protocol - [ ] Connects to configurable Ollama base URL (default: `http://localhost:11434`) - [ ] Supports any model available in the local Ollama instance - [ ] Streaming responses supported via Ollama streaming API - [ ] Graceful error when Ollama is not running - [ ] Test coverage >= 97% ## Metadata - **Commit Message**: `feat(providers): implement OllamaProvider for local model support` - **Branch**: `feature/v3.6.0/ollama-provider` - **Milestone**: v3.6.0 - **Ref**: #5174 EPIC: Additional LLM Provider Integrations — Gemini, Mistral, Local Models (v3.6.0) ## Subtasks - [ ] Define `OllamaProvider` class implementing provider protocol - [ ] Implement configurable base URL via actor YAML `provider.base_url` - [ ] Implement streaming chat completion with Ollama REST API - [ ] Implement capability detection (tool use availability per model) - [ ] Write unit tests with mocked Ollama API responses ## Definition of Done - Implementation complete and all acceptance criteria met - Tests written and passing (coverage >= 97%) - PR reviewed and merged - Parent epic updated --- **Automated by CleverAgents Bot** Supervisor: Epic Planning | Agent: epic-planning-pool-supervisor
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#10133
No description provided.