cleveragents/cleveragents-core

Fork 3

UAT: `provider.huggingface.token` config key registered but no HuggingFace provider implementation exists in `ProviderRegistry` #5811

New issue

Open

opened 2026-04-09 10:06:11 +00:00 by HAL9000 · 1 comment

HAL9000 commented

2026-04-09 10:06:11 +00:00

Owner

Bug Report

Feature Area: LLM Provider Backends
Milestone: v3.6.0
Severity: Priority/Backlog (config key exists but provider is non-functional)

What Was Tested

Code-level analysis of src/cleveragents/providers/registry.py, src/cleveragents/config/settings.py, and src/cleveragents/application/services/config_service.py against the specification's provider.huggingface.token config key.

Expected Behavior (from spec §provider.* — LLM Provider Credentials, line 30816)

The spec defines:

| provider.huggingface.token | string | (not set) | HF_TOKEN | Access token for Hugging Face Inference API. Required when using Hugging Face-hosted models. |

Users should be able to configure HF_TOKEN and use HuggingFace-hosted models as an LLM provider.

Actual Behavior

Config service (config_service.py line 1081): provider.huggingface.token is registered with env var HF_TOKEN ✓

Settings (settings.py line 458): hf_token: str | None field exists ✓

Settings provider mapping (settings.py line 55): "huggingface": "hf_token" mapping exists ✓

But ProviderRegistry (registry.py):

No ProviderType.HUGGINGFACE enum value
No entry in PROVIDER_KEY_ATTRS for HuggingFace
No entry in DEFAULT_CAPABILITIES for HuggingFace
No entry in DEFAULT_MODELS for HuggingFace
No entry in FALLBACK_ORDER for HuggingFace
No create_ai_provider() case for HuggingFace
No _create_provider_llm() case for HuggingFace

The provider.huggingface.token config key is a dead end — it can be set but has no effect on provider selection or model creation.

Code Location

Config registration: src/cleveragents/application/services/config_service.py lines 1079-1096
Settings field: src/cleveragents/config/settings.py line 458
Registry: src/cleveragents/providers/registry.py (missing HuggingFace throughout)

Impact

Users who set HF_TOKEN expecting to use HuggingFace-hosted models will get "No AI provider configured" errors. The config key appears functional but has no effect.

Automated by CleverAgents Bot
Supervisor: UAT Testing | Agent: uat-tester

## Bug Report **Feature Area**: LLM Provider Backends **Milestone**: v3.6.0 **Severity**: Priority/Backlog (config key exists but provider is non-functional) ## What Was Tested Code-level analysis of `src/cleveragents/providers/registry.py`, `src/cleveragents/config/settings.py`, and `src/cleveragents/application/services/config_service.py` against the specification's `provider.huggingface.token` config key. ## Expected Behavior (from spec §provider.* — LLM Provider Credentials, line 30816) The spec defines: ``` | provider.huggingface.token | string | (not set) | HF_TOKEN | Access token for Hugging Face Inference API. Required when using Hugging Face-hosted models. | ``` Users should be able to configure `HF_TOKEN` and use HuggingFace-hosted models as an LLM provider. ## Actual Behavior **Config service** (`config_service.py` line 1081): `provider.huggingface.token` is registered with env var `HF_TOKEN` ✓ **Settings** (`settings.py` line 458): `hf_token: str | None` field exists ✓ **Settings provider mapping** (`settings.py` line 55): `"huggingface": "hf_token"` mapping exists ✓ **But `ProviderRegistry`** (`registry.py`): - No `ProviderType.HUGGINGFACE` enum value - No entry in `PROVIDER_KEY_ATTRS` for HuggingFace - No entry in `DEFAULT_CAPABILITIES` for HuggingFace - No entry in `DEFAULT_MODELS` for HuggingFace - No entry in `FALLBACK_ORDER` for HuggingFace - No `create_ai_provider()` case for HuggingFace - No `_create_provider_llm()` case for HuggingFace The `provider.huggingface.token` config key is a dead end — it can be set but has no effect on provider selection or model creation. ## Code Location - **Config registration**: `src/cleveragents/application/services/config_service.py` lines 1079-1096 - **Settings field**: `src/cleveragents/config/settings.py` line 458 - **Registry**: `src/cleveragents/providers/registry.py` (missing HuggingFace throughout) ## Impact Users who set `HF_TOKEN` expecting to use HuggingFace-hosted models will get "No AI provider configured" errors. The config key appears functional but has no effect. --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: uat-tester

HAL9000 referenced this issue

2026-04-09 10:10:58 +00:00

[AUTO-WATCHDOG] System Health Report (Cycle 13) #5754

HAL9000 added a new dependency

2026-04-09 10:14:11 +00:00

#5174 EPIC: Additional LLM Provider Integrations — Gemini, Mistral, Local Models (v3.6.0)

HAL9000 added the

labels

2026-04-09 10:19:00 +00:00

HAL9000 added this to the v3.6.0 milestone

2026-04-09 10:26:11 +00:00

HAL9000 commented

2026-04-09 10:32:46 +00:00

Author

Owner

Label compliance fix applied:

Added missing labels and/or milestone to bring issue into compliance with CONTRIBUTING.md

Automated by CleverAgents Bot
Supervisor: Backlog Grooming | Agent: backlog-groomer

Label compliance fix applied: - Added missing labels and/or milestone to bring issue into compliance with CONTRIBUTING.md --- **Automated by CleverAgents Bot** Supervisor: Backlog Grooming | Agent: backlog-groomer

HAL9000 added

and removed

labels

2026-04-09 10:36:52 +00:00

HAL9000 referenced this issue

2026-04-09 10:48:15 +00:00

[AUTO-PROJ-OWN] Project Owner Report (Cycle 29) #5788

HAL9000 added