Epic: Additional LLM Provider Integrations — Cohere, Groq, Together AI, and Provider Abstraction #3365

Open
opened 2026-04-05 14:38:38 +00:00 by freemo · 2 comments
Owner

Metadata

  • Branch Naming Convention: feat/v3.6.0/llm-providers
  • Milestone: v3.6.0

Background and Context

The v3.6.0 milestone scope includes "Additional LLM backends and provider integrations." Currently, Cohere, Groq, and Together AI providers lack dedicated provider classes and are only handled via generic LangChain dynamic imports. The actor configuration supports a config.provider field referencing openai, anthropic, google, azure, openrouter, etc., but several providers are missing first-class implementations.

This Epic groups all work required to add dedicated provider classes for missing LLM backends, improve provider abstraction, and ensure all spec-referenced providers are properly integrated.

Child Issues

  • #3366 — feat(providers): implement dedicated Cohere provider class with LangChain integration
  • #3367 — feat(providers): implement dedicated Groq provider class with LangChain integration
  • #3368 — feat(providers): implement dedicated Together AI provider class with LangChain integration
  • #3369 — feat(providers): implement Hugging Face provider class for local and hosted model inference

Definition of Done

  • All child issues are closed
  • Cohere, Groq, and Together AI have dedicated provider classes
  • Provider abstraction layer supports easy addition of new providers
  • All nox stages pass
  • Coverage >= 97%

Automated by CleverAgents Bot
Supervisor: Unknown | Agent: ca-epic-planner

## Metadata - **Branch Naming Convention**: `feat/v3.6.0/llm-providers` - **Milestone**: v3.6.0 ## Background and Context The v3.6.0 milestone scope includes "Additional LLM backends and provider integrations." Currently, Cohere, Groq, and Together AI providers lack dedicated provider classes and are only handled via generic LangChain dynamic imports. The actor configuration supports a `config.provider` field referencing `openai`, `anthropic`, `google`, `azure`, `openrouter`, etc., but several providers are missing first-class implementations. This Epic groups all work required to add dedicated provider classes for missing LLM backends, improve provider abstraction, and ensure all spec-referenced providers are properly integrated. ## Child Issues - [ ] #3366 — feat(providers): implement dedicated Cohere provider class with LangChain integration - [ ] #3367 — feat(providers): implement dedicated Groq provider class with LangChain integration - [ ] #3368 — feat(providers): implement dedicated Together AI provider class with LangChain integration - [ ] #3369 — feat(providers): implement Hugging Face provider class for local and hosted model inference ## Definition of Done - [ ] All child issues are closed - [ ] Cohere, Groq, and Together AI have dedicated provider classes - [ ] Provider abstraction layer supports easy addition of new providers - [ ] All nox stages pass - [ ] Coverage >= 97% --- **Automated by CleverAgents Bot** Supervisor: Unknown | Agent: ca-epic-planner
freemo added this to the v3.6.0 milestone 2026-04-05 14:38:43 +00:00
Author
Owner

Child Issues Created

The following child issues have been created for this Epic:

# Title Status
#3366 feat(providers): implement dedicated Cohere provider class with LangChain integration Open
#3367 feat(providers): implement dedicated Groq provider class with LangChain integration Open
#3368 feat(providers): implement dedicated Together AI provider class with LangChain integration Open
#3369 feat(providers): implement Hugging Face provider class for local and hosted model inference Open

All child issues block this Epic via Forgejo dependency links.

Dependency Chain:

#3366 (Cohere) ──┐
#3367 (Groq)   ──┤──▶ #3365 (Epic: LLM Providers)
#3368 (Together)─┤
#3369 (HuggingFace)─┘

Automated by CleverAgents Bot
Supervisor: Unknown | Agent: ca-epic-planner

## Child Issues Created The following child issues have been created for this Epic: | # | Title | Status | |---|-------|--------| | #3366 | feat(providers): implement dedicated Cohere provider class with LangChain integration | Open | | #3367 | feat(providers): implement dedicated Groq provider class with LangChain integration | Open | | #3368 | feat(providers): implement dedicated Together AI provider class with LangChain integration | Open | | #3369 | feat(providers): implement Hugging Face provider class for local and hosted model inference | Open | All child issues block this Epic via Forgejo dependency links. **Dependency Chain:** ``` #3366 (Cohere) ──┐ #3367 (Groq) ──┤──▶ #3365 (Epic: LLM Providers) #3368 (Together)─┤ #3369 (HuggingFace)─┘ ``` --- **Automated by CleverAgents Bot** Supervisor: Unknown | Agent: ca-epic-planner
Author
Owner

Issue triaged by project owner:

  • State: Verified
  • Priority: High — The v3.6.0 milestone explicitly scopes "Additional LLM backends and provider integrations." This Epic groups the work to add dedicated provider classes for Cohere, Groq, Together AI, and Hugging Face.
  • Milestone: v3.6.0 (already set)
  • Story Points: 13 — XXL — This Epic encompasses 4 child issues, each requiring a new provider class with LangChain integration, tests, and documentation. Estimated 1+ week total.
  • MoSCoW: Should Have — While the specification mentions these providers and v3.6.0 scopes them, the existing generic LangChain dynamic import path provides functional (if not first-class) support. These are important for production readiness but not strictly blocking other Must Have work.
  • Child Issues: #3366, #3367, #3368, #3369

Automated by CleverAgents Bot
Supervisor: Project Owner | Agent: ca-project-owner

Issue triaged by project owner: - **State**: Verified - **Priority**: High — The v3.6.0 milestone explicitly scopes "Additional LLM backends and provider integrations." This Epic groups the work to add dedicated provider classes for Cohere, Groq, Together AI, and Hugging Face. - **Milestone**: v3.6.0 (already set) - **Story Points**: 13 — XXL — This Epic encompasses 4 child issues, each requiring a new provider class with LangChain integration, tests, and documentation. Estimated 1+ week total. - **MoSCoW**: Should Have — While the specification mentions these providers and v3.6.0 scopes them, the existing generic LangChain dynamic import path provides functional (if not first-class) support. These are important for production readiness but not strictly blocking other Must Have work. - **Child Issues**: #3366, #3367, #3368, #3369 --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: ca-project-owner
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.

Depends on
Reference
cleveragents/cleveragents-core#3365
No description provided.