generated from coulomb/repo-seed
tegwick
3ea9366c5a
Honest first-pass maturity vector grounded in README/docs/tests present in this repo; no invented evidence. Flagged for human review before publish. See reuse-surface history/2026-07-06-coverage-classification.md. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
124 lines
4.5 KiB
Markdown
124 lines
4.5 KiB
Markdown
---
|
|
id: capability.agents.llm-connector
|
|
name: Pluggable LLM Adapter Library (llm-connect)
|
|
summary: Provider-neutral Python/CLI LLM adapter library supporting OpenRouter, Gemini, OpenAI, and the
|
|
Claude Code CLI out of the box, with a clean abstract interface for adding new providers.
|
|
owner: llm-connect
|
|
status: draft
|
|
domain: agents
|
|
tags:
|
|
- llm
|
|
- adapter
|
|
- provider-neutral
|
|
maturity:
|
|
discovery:
|
|
current: D3
|
|
target: D5
|
|
confidence: medium
|
|
rationale: README documents a working quick-start (`create_adapter`, `RunConfig`, `execute_prompt`),
|
|
the supported provider list, and both local-editable and future-published install paths.
|
|
availability:
|
|
current: A2
|
|
target: A3
|
|
confidence: medium
|
|
rationale: Installable today via `pip install -e` (local) with a documented future `pip install llm-connect`
|
|
path once published; consumed today by sibling repos including `cya` (can-you-assist) and referenced
|
|
as the intended backend for reuse-surface's own `establish --discover`.
|
|
external_evidence:
|
|
completeness:
|
|
level: C2
|
|
confidence: low
|
|
basis: scope_vs_intent_and_consumer_expectations
|
|
satisfied_expectations:
|
|
- four providers implemented (OpenRouter, Gemini, OpenAI, Claude Code CLI)
|
|
- abstract adapter interface for adding new providers
|
|
- already a named integration point for other repos (can-you-assist's LLMAdapter seam, reuse-surface's
|
|
establish --discover)
|
|
broken_expectations: []
|
|
out_of_scope_expectations: []
|
|
reliability:
|
|
level: R1
|
|
confidence: low
|
|
basis: consumer_quality_signals
|
|
known_reliability_risks:
|
|
- no llm-connect instance was running on this workstation during the REUSE-WP-0017 sweep, so establish
|
|
--discover fell back to manual authoring for this campaign
|
|
discovery:
|
|
intent: Give Python and CLI consumers a single, provider-neutral way to call LLMs, decoupling agent/tool
|
|
code from any one vendor's SDK.
|
|
includes:
|
|
- provider-neutral adapter interface
|
|
- OpenRouter, Gemini, OpenAI, Claude Code CLI adapters
|
|
- RunConfig-based execution
|
|
excludes:
|
|
- hosting or credential custody for providers (routes to OpenBao/operator paths per credential-routing
|
|
conventions)
|
|
assumptions: []
|
|
use_cases: []
|
|
research_memos: []
|
|
availability:
|
|
current_level: A2
|
|
target_level: A3
|
|
current_artifacts:
|
|
- Python package (`llm_connect`)
|
|
target_artifacts: []
|
|
consumption_modes:
|
|
- library import
|
|
- cli
|
|
relations:
|
|
depends_on: []
|
|
supports: []
|
|
related_to: []
|
|
evidence:
|
|
documentation:
|
|
- README.md
|
|
tests:
|
|
- tests/
|
|
consumer_feedback: []
|
|
bug_reports: []
|
|
incidents: []
|
|
consumer_guidance:
|
|
recommended_for:
|
|
- any repo needing provider-neutral LLM calls instead of a vendor-specific SDK
|
|
not_recommended_for:
|
|
- needs requiring a provider not yet adapted (extend via the abstract interface first)
|
|
known_limitations:
|
|
- not yet published to a package index; local editable install only
|
|
promotion_history: []
|
|
---
|
|
|
|
# Pluggable LLM Adapter Library (llm-connect)
|
|
|
|
## Overview
|
|
|
|
`llm-connect` provides pluggable, provider-neutral LLM adapters for Python and the command line, supporting OpenRouter, Gemini, OpenAI, and the Claude Code CLI out of the box behind a clean abstract interface, and is already the intended backend for several sibling repos including `can-you-assist` and `reuse-surface`'s own drafting tooling.
|
|
|
|
## Assessment notes
|
|
|
|
### Discovery
|
|
|
|
README documents a working quick-start (`create_adapter`, `RunConfig`, `execute_prompt`), the supported provider list, and both local-editable and future-published install paths.
|
|
|
|
### Availability
|
|
|
|
Installable today via `pip install -e` (local) with a documented future `pip install llm-connect` path once published; consumed today by sibling repos including `cya` (can-you-assist) and referenced as the intended backend for reuse-surface's own `establish --discover`.
|
|
|
|
### Completeness
|
|
|
|
First-pass honest assessment from the REUSE-WP-0017 coverage campaign
|
|
(reuse-surface). No external consumer feedback exists yet; levels reflect
|
|
scope-vs-intent documentation quality, not internal code quality.
|
|
|
|
### Reliability
|
|
|
|
No production consumer telemetry exists yet; reliability level is
|
|
intentionally conservative pending REUSE-WP-0019 reuse-telemetry evidence.
|
|
|
|
## Promotion checklist
|
|
|
|
- [x] ID follows `capability.<domain>.<name>` pattern
|
|
- [x] Maturity enums match `specs/CapabilityMaturityStandard.md`
|
|
- [x] `external_evidence` is populated separately from `maturity`
|
|
- [ ] Relations reference valid capability IDs (none yet)
|
|
- [x] Index entry added in `registry/indexes/capabilities.yaml`
|