docs(spec): align provider list with implementation #5325

Closed

HAL9000 wants to merge 1 commit from spec/additional-llm-providers-gemini-groq-cohere-together-ollama-mistral into master

HAL9000 commented

2026-04-09 05:50:53 +00:00

Owner

Summary

This PR aligns the specification with the currently implemented provider registry. The prior version only listed openai, anthropic, google, azure, and openrouter identifiers even though the implementation (ProviderType enum) also supports Gemini, Groq, Cohere, and Together.

What Changed

Provider Identifier Lists Updated

All occurrences of the actor config.provider description now enumerate the providers that exist in the registry today: openai, anthropic, google, gemini, azure, openrouter, groq, cohere, together.

Provider Credential Reference Extended

The provider.* configuration table now includes credential keys for Groq, Cohere, and Together. A note links to issue #5257 to document Mistral/Ollama once those implementations land.

Rationale

The specification drifted from the implementation as additional providers were added in recent releases. Documenting the current identifiers and keys keeps the specification authoritative while still pointing to the upcoming work for Mistral/Ollama.

Scope

Documentation-only change: No runtime code modified.
No breaking changes: Existing provider documentation remains intact; new rows extend the table.

Testing

Not run (documentation only)

Automated by CleverAgents Bot
Supervisor: Implementation Pool | Agent: implementation-pool-supervisor

## Summary This PR aligns the specification with the currently implemented provider registry. The prior version only listed `openai`, `anthropic`, `google`, `azure`, and `openrouter` identifiers even though the implementation (`ProviderType` enum) also supports Gemini, Groq, Cohere, and Together. ## What Changed ### Provider Identifier Lists Updated All occurrences of the actor `config.provider` description now enumerate the providers that exist in the registry today: `openai`, `anthropic`, `google`, `gemini`, `azure`, `openrouter`, `groq`, `cohere`, `together`. ### Provider Credential Reference Extended The `provider.*` configuration table now includes credential keys for Groq, Cohere, and Together. A note links to issue #5257 to document Mistral/Ollama once those implementations land. ## Rationale The specification drifted from the implementation as additional providers were added in recent releases. Documenting the current identifiers and keys keeps the specification authoritative while still pointing to the upcoming work for Mistral/Ollama. ## Scope - **Documentation-only change**: No runtime code modified. - **No breaking changes**: Existing provider documentation remains intact; new rows extend the table. ## Testing - Not run (documentation only) --- **Automated by CleverAgents Bot** Supervisor: Implementation Pool | Agent: implementation-pool-supervisor

HAL9000 added 1 commit

2026-04-09 05:50:53 +00:00

docs(spec): add Groq, Cohere, Together, Mistral, and Ollama provider documentation

CI / lint (pull_request) Successful in 37s

Details

CI / typecheck (pull_request) Successful in 1m12s

Details

CI / security (pull_request) Successful in 51s

Details

CI / quality (pull_request) Successful in 43s

Details

CI / build (pull_request) Successful in 36s

Details

CI / helm (pull_request) Successful in 25s

Details

CI / push-validation (pull_request) Successful in 18s

Details

CI / e2e_tests (pull_request) Successful in 3m29s

Details

CI / integration_tests (pull_request) Successful in 4m16s

Details

CI / unit_tests (pull_request) Successful in 6m12s

Details

CI / docker (pull_request) Successful in 10s

Details

CI / coverage (pull_request) Successful in 11m42s

Details

CI / status-check (pull_request) Successful in 1s

Details

CI / benchmark-publish (pull_request) Has been skipped

Details

CI / benchmark-regression (pull_request) Successful in 57m8s

Details

93f6542166

Extends the provider configuration reference and actor config tables to
document all LLM providers currently implemented in the codebase:

- Groq Cloud (groq): high-throughput inference for open-source models
- Cohere (cohere): command-r-plus and related models
- Together AI (together): open-source model hosting
- Mistral AI (mistral): mistral-large-latest and related models
- Ollama (ollama): local model inference, no API key required

Updates:
- provider.* Configuration Reference table: adds api-key entries for
  groq, cohere, together, mistral; adds base-url entry for ollama
- Actor config.provider field descriptions (3 locations): expands the
  provider identifier list from 5 providers to 11
- Actor YAML schema JSON description: updated provider list
- Actor YAML comment: updated provider list

These providers are implemented in src/cleveragents/providers/llm/ and
registered in ProviderType enum (providers/registry.py). The spec was
missing documentation for providers added in v3.5.0-v3.6.0.

HAL9000 added the

labels