forked from EduCraft/curriculum-project-hub
64 lines
2.8 KiB
Markdown
64 lines
2.8 KiB
Markdown
# ADR 0017: Agent Runtime — Claude Code SDK via OpenRouter
|
|
|
|
## Status
|
|
|
|
Accepted.
|
|
|
|
## Context
|
|
|
|
The original ADR-0017 mandated a provider-agnostic agent layer: any
|
|
OpenAI-compatible model via OpenRouter, custom agent loop built on Vercel AI
|
|
SDK's `streamText`. The motivation was to avoid vendor lock-in.
|
|
|
|
In practice, the hand-rolled agent loop lacked capabilities that a production
|
|
agent needs: context compaction (long conversations), tool approval flows,
|
|
partial-message streaming, and a battle-tested multi-turn loop. Building these
|
|
ourselves meant re-implementing what the Claude Code SDK already provides.
|
|
|
|
The Feishu integration also proved costly to hand-roll — card schema quirks,
|
|
patch limitations, file support — each API quirk cost a round-trip.
|
|
|
|
## Decision
|
|
|
|
Adopt `@anthropic-ai/claude-agent-sdk` as the agent runtime, routed through
|
|
OpenRouter's **"Anthropic Skin"** (`https://openrouter.ai/api`).
|
|
|
|
OpenRouter exposes an Anthropic Messages API-compatible endpoint. Claude Code
|
|
SDK speaks its native protocol directly to OpenRouter — no proxy, no format
|
|
conversion. The SDK's `query()` owns the agent loop (tool dispatch, compaction,
|
|
streaming). Built-in tools (Read, Write, Bash, Glob, Grep) cover the entire
|
|
tool surface — no custom tools needed. `cph check` / `cph build` run via Bash.
|
|
|
|
The Hub `AgentSession` remains provider/model-bound, but it must persist the
|
|
provider runtime cursor needed to continue a conversation. For Claude Code SDK,
|
|
that cursor is the `result.session_id`; store it in `AgentSession.metadata` as
|
|
`claudeSessionId` and pass it back to the next `query()` call as
|
|
`options.resume`.
|
|
|
|
Environment variables:
|
|
```
|
|
ANTHROPIC_BASE_URL=https://openrouter.ai/api
|
|
ANTHROPIC_AUTH_TOKEN=<OpenRouter API key>
|
|
ANTHROPIC_API_KEY="" # must be explicitly empty
|
|
```
|
|
|
|
Model routing: `ANTHROPIC_DEFAULT_SONNET_MODEL` etc. accept OpenRouter model
|
|
IDs (e.g. `z-ai/glm-4.7`, `anthropic/claude-sonnet-4-20250514`). This means
|
|
**provider-agnosticism is preserved** — any OpenRouter model that supports tool
|
|
use can be used, not just Anthropic models.
|
|
|
|
## Consequences
|
|
|
|
- Provider-agnosticism preserved via OpenRouter — GLM, Claude, GPT, etc. all
|
|
work as long as the model supports tool use.
|
|
- The agent loop is Claude Code SDK's (compaction, tool approval, partial
|
|
message streaming) — not hand-rolled.
|
|
- Custom tools (read_file, write_file, cph_check, cph_build) are replaced by
|
|
the SDK's built-in Read/Write/Bash/Glob/Grep.
|
|
- The SSE event format matches Claude-to-IM's expected protocol natively.
|
|
- Per-run model selection works via role→model mapping; models are OpenRouter
|
|
IDs, not Anthropic-only aliases.
|
|
- OpenRouter recommends setting Anthropic as the top-priority provider for
|
|
Claude Code; non-Anthropic models may have reduced compatibility with some
|
|
SDK features (e.g. thinking blocks).
|