Skip to content

boost-backend-module-llamastack — Llama Stack provider module (issue 10 of 15) #3306

@gabemontero

Description

@gabemontero

Labels: ready-to-code
Depends on: Issue 2

Create the Llama Stack provider module as an independent createBackendModule with ResponsesApiProvider, OpenAI Agent SDK orchestration, and all provider caches using cacheService.

Tasks

From openspec/changes/pluggable-ai-platform-architecture/tasks.md sections 2 and 3:

  • 2.1 Create boost-backend-module-llamastack package
  • 2.2 Implement ResponsesApiProvider and ResponsesApiProviderFactory
  • 3.2 Implement model list cache via cache.withOptions({ defaultTtl: '60s' })
  • 3.5 Implement MCP auth token cache via cacheService
  • 3.8 Implement client manager cache as identity-keyed cacheService
  • 3b.2 Define Llama Stack-specific types in module only

From openspec/changes/platform-operations-deployment/tasks.md:

  • 1.5 Provider session maps: cacheService with session-appropriate TTL
  • 1.6 ClientManager: identity-keyed cacheService

Specifications

  • openspec/changes/pluggable-ai-platform-architecture/specs/provider-packaging/spec.md — Llama Stack module scenarios
  • openspec/changes/pluggable-ai-platform-architecture/specs/multi-agent-orchestration/spec.md
  • openspec/changes/pluggable-ai-platform-architecture/design.md — Decision 2 (modules not plugins), Decision 3 (cacheService)

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions