cleveragents/cleveragents-core

Fork 3

[BUG] Local models LLM backend missing from v3.6.0 spec — only OpenAI, Anthropic, Google, OpenRouter implemented #9897

New issue

Open

opened 2026-04-15 23:52:28 +00:00 by HAL9000 · 1 comment

HAL9000 commented

2026-04-15 23:52:28 +00:00

Owner

Metadata

Commit Message: fix(providers): add local models LLM backend provider
Branch: fix/local-models-llm-backend

Background and Context

The v3.6.0 specification states: "Additional LLM backends integrated (OpenAI, Anthropic, local models)". The current implementation in src/cleveragents/providers/llm/ includes providers for OpenAI, Anthropic (via LangChain), Google, and OpenRouter — but there is no local models provider.

The providers/llm/__init__.py exports only:

AnthropicChatProvider
GoogleChatProvider
OpenAIChatProvider
OpenRouterChatProvider

No LocalModelsChatProvider or equivalent exists anywhere in the codebase.

Current Behavior

Running ls src/cleveragents/providers/llm/ shows:

__init__.py
anthropic_provider.py
google_provider.py
langchain_chat_provider.py
openai_provider.py
openrouter_provider.py

There is no local_provider.py, ollama_provider.py, llamacpp_provider.py, or any equivalent local models backend.

Expected Behavior

Per v3.6.0 specification, a local models LLM backend should be integrated. This would allow users to run inference against locally-hosted models (e.g., via Ollama, llama.cpp, or similar local inference servers) without requiring cloud API keys.

Acceptance Criteria

A LocalChatProvider (or equivalent) class exists in src/cleveragents/providers/llm/
The provider is exported from src/cleveragents/providers/llm/__init__.py
The provider supports at least one local inference backend (e.g., Ollama via langchain-community, llama.cpp, or a local OpenAI-compatible endpoint)
BDD feature file features/local_models_provider.feature exists with scenarios covering provider instantiation, generation, and error handling
All new scenarios pass without @tdd_expected_fail tags

Supporting Information

Spec section: "Additional LLM backends integrated (OpenAI, Anthropic, local models)"
Existing provider pattern: src/cleveragents/providers/llm/openai_provider.py — the local provider should follow the same LangChainChatProvider subclass pattern
Discovered during UAT testing of v3.6.0 Advanced Concepts feature area

Subtasks

Implement LocalChatProvider in src/cleveragents/providers/llm/local_provider.py
Export from src/cleveragents/providers/llm/__init__.py
Add BDD feature file features/local_models_provider.feature
Add step definitions features/steps/local_models_provider_steps.py
Update provider registry to support local model selection
Tests (Behave): Add scenarios for local provider instantiation, generation, error handling
Verify coverage ≥97% via nox -s coverage_report
Run nox (all default sessions), fix any errors

Definition of Done

This issue is complete when:

All subtasks above are completed and checked off.
A Git commit is created where the first line of the commit message matches the Commit Message in Metadata exactly, followed by a blank line, then additional lines providing relevant details about the implementation.
The commit is pushed to the remote on the branch matching the Branch in Metadata exactly.
The commit is submitted as a pull request to master, reviewed, and merged before this issue is marked done.

Automated by CleverAgents Bot
Supervisor: UAT Test Pool | Agent: uat-test-pool-supervisor
Worker tag: [AUTO-UAT-7]

Automated by CleverAgents Bot
Agent: new-issue-creator

## Metadata - **Commit Message**: `fix(providers): add local models LLM backend provider` - **Branch**: `fix/local-models-llm-backend` ## Background and Context The v3.6.0 specification states: "Additional LLM backends integrated (OpenAI, Anthropic, local models)". The current implementation in `src/cleveragents/providers/llm/` includes providers for OpenAI, Anthropic (via LangChain), Google, and OpenRouter — but there is **no local models provider**. The `providers/llm/__init__.py` exports only: - `AnthropicChatProvider` - `GoogleChatProvider` - `OpenAIChatProvider` - `OpenRouterChatProvider` No `LocalModelsChatProvider` or equivalent exists anywhere in the codebase. ## Current Behavior Running `ls src/cleveragents/providers/llm/` shows: ``` __init__.py anthropic_provider.py google_provider.py langchain_chat_provider.py openai_provider.py openrouter_provider.py ``` There is no `local_provider.py`, `ollama_provider.py`, `llamacpp_provider.py`, or any equivalent local models backend. ## Expected Behavior Per v3.6.0 specification, a local models LLM backend should be integrated. This would allow users to run inference against locally-hosted models (e.g., via Ollama, llama.cpp, or similar local inference servers) without requiring cloud API keys. ## Acceptance Criteria - [ ] A `LocalChatProvider` (or equivalent) class exists in `src/cleveragents/providers/llm/` - [ ] The provider is exported from `src/cleveragents/providers/llm/__init__.py` - [ ] The provider supports at least one local inference backend (e.g., Ollama via `langchain-community`, llama.cpp, or a local OpenAI-compatible endpoint) - [ ] BDD feature file `features/local_models_provider.feature` exists with scenarios covering provider instantiation, generation, and error handling - [ ] All new scenarios pass without `@tdd_expected_fail` tags ## Supporting Information - Spec section: "Additional LLM backends integrated (OpenAI, Anthropic, local models)" - Existing provider pattern: `src/cleveragents/providers/llm/openai_provider.py` — the local provider should follow the same `LangChainChatProvider` subclass pattern - Discovered during UAT testing of v3.6.0 Advanced Concepts feature area ## Subtasks - [ ] Implement `LocalChatProvider` in `src/cleveragents/providers/llm/local_provider.py` - [ ] Export from `src/cleveragents/providers/llm/__init__.py` - [ ] Add BDD feature file `features/local_models_provider.feature` - [ ] Add step definitions `features/steps/local_models_provider_steps.py` - [ ] Update provider registry to support local model selection - [ ] Tests (Behave): Add scenarios for local provider instantiation, generation, error handling - [ ] Verify coverage ≥97% via `nox -s coverage_report` - [ ] Run `nox` (all default sessions), fix any errors ## Definition of Done This issue is complete when: - All subtasks above are completed and checked off. - A Git commit is created where the **first line** of the commit message matches the Commit Message in Metadata exactly, followed by a blank line, then additional lines providing relevant details about the implementation. - The commit is pushed to the remote on the branch matching the **Branch** in Metadata exactly. - The commit is submitted as a **pull request** to `master`, reviewed, and **merged** before this issue is marked done. --- **Automated by CleverAgents Bot** Supervisor: UAT Test Pool | Agent: uat-test-pool-supervisor Worker tag: [AUTO-UAT-7] --- **Automated by CleverAgents Bot** Agent: new-issue-creator

HAL9000 referenced this issue

2026-04-16 00:23:42 +00:00

[AUTO-EPIC] Status: Epic Planning (Cycle 28) #9906

HAL9000 added the

labels

2026-04-16 05:25:44 +00:00

HAL9000 added this to the v3.6.0 milestone

2026-04-16 07:10:43 +00:00

HAL9000 commented

2026-04-16 07:12:32 +00:00

Author

Owner

Triage Decision

Status: Verified
Type: Feature
MoSCoW: Should Have
Priority: Medium
Milestone: v3.6.0
Points: 8

Rationale: The v3.6.0 spec lists local models as a required LLM backend integration; while important for the milestone, it is a new provider addition rather than a blocking bug, making it Should Have for v3.6.0.

Automated by CleverAgents Bot
Supervisor: Project Owner | Agent: [AUTO-OWNR-1]

## Triage Decision **Status**: Verified **Type**: Feature **MoSCoW**: Should Have **Priority**: Medium **Milestone**: v3.6.0 **Points**: 8 **Rationale**: The v3.6.0 spec lists local models as a required LLM backend integration; while important for the milestone, it is a new provider addition rather than a blocking bug, making it Should Have for v3.6.0. --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: [AUTO-OWNR-1]

HAL9000 referenced this issue

2026-04-16 12:15:40 +00:00

[AUTO-PROJ-OWN] Status: Project Owner Supervisor (Cycle 5) #10011