feat: Plexum-minimax-provider v0.1 — MiniMax via Anthropic-compat endpoint

Plexum ProviderPlugin that serves MiniMax models through MiniMax's
Anthropic-compatible HTTP endpoint
(https://api.minimax.io/anthropic, or CN api.minimaxi.com). Inspired
by openclaw's extensions/minimax provider-registration, but rewritten
in Go for Plexum's SDK.

internal/anthropic/ (~210 LOC + 6 tests):
- minimal HTTP+SSE Anthropic Messages client (POST /v1/messages,
  stream:true, parses event:/data: SSE frames)
- handles non-2xx as HTTP error; stream errors land as Event{Type:"error"}
- 1 MiB SSE line cap; per-conn 5min timeout

internal/translate/ (~220 LOC):
- CanonicalToAnthropic: canonical.TurnRequest → MessagesRequest
- blockToAnthropic: TextBlock / ToolUseBlock / ToolResultBlock /
  ThinkingBlock → loose ContentBlock map; preserves signatures + cache
  control
- Translator: per-turn state machine; consumes anthropic.Event stream
  and emits canonical.TurnEvent stream (handles thinking blocks +
  tool_use input_json_delta accumulation + signature_delta capture)

cmd/plexum-minimax-provider-plugin/:
- Plugin manifest declares provider.models = [MiniMax-M2.7,
  MiniMax-M2.7-highspeed]
- Backend fixed to "api" (per scope); region "global"|"cn" + base_url
  override supported via config
- HostConfig from <profile>/plugins/plexum-minimax-provider/config.json
  {api_key, region?, base_url?, max_tokens_default?}

scripts/install.sh: build + manifest emit; operator writes config.json
+ allows plugin + adds an agent + restarts.

End-to-end verified against the real key:
1. plexum say --agent-id mini ... → "Hi, I'm MiniMax!"
2. Multi-turn continuity: agent recalled the prior reply
3. Via gateway socket: {"outcome":"text","text":"\n\npong"}
4. Via Fabric channel (alice posts → plugin inbound → mini agent
   → MiniMax → outbound REST → reply visible in bt2-clean seq=11):
     "Hi there! 👋 Fun fact: Octopuses have three hearts, blue blood,
      and neurons distributed throughout their arms—so their tentacles
      can 'think'"

The MiniMax-M2.7-highspeed variant works the same way but hit a
Code Plan rate-limit ceiling during testing (not a plugin issue).

Deferred:
- OAuth (Code Plan portal) — not in v1 scope per request
- MiniMax Portal provider (separate provider id minimax-portal)
- Image / TTS / video / music providers (separate plugins later)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
h z
2026-05-31 16:01:38 +01:00
commit e44936990c
7 changed files with 1031 additions and 0 deletions

69
README.md Normal file
View File

@@ -0,0 +1,69 @@
# Plexum-minimax-provider
Plexum ProviderPlugin that serves **MiniMax** models via MiniMax's
Anthropic-compatible HTTP endpoint.
## Status
**v0.1 — current**: API key auth, streaming SSE, declared models
`MiniMax-M2.7` + `MiniMax-M2.7-highspeed`. Backend fixed to `api`
(global `https://api.minimax.io/anthropic` or CN `https://api.minimaxi.com/anthropic`).
**Deferred**: OAuth (Code Plan portal), MiniMax Portal provider, image /
TTS / video / music providers (separate plugins later if wanted).
## Install
```bash
cd ~/Plexum-minimax-provider
./scripts/install.sh
```
Then:
1. **Write API key** to `~/.plexum/plugins/plexum-minimax-provider/config.json`:
```json
{
"api_key": "sk-cp-..."
}
```
(`chmod 600` it.)
2. **Allow the plugin** in `~/.plexum/plexum.json`:
```json
{"plugins": {"allow": ["plexum-minimax-provider"]}}
```
3. **Point an agent at a MiniMax model**:
```bash
plexum agent-add --model MiniMax-M2.7 my-agent
```
4. **Restart** the gateway and talk:
```bash
systemctl --user restart plexum
plexum say --agent-id my-agent --session-id $(plexum new-session --agent-id my-agent) "hello"
```
## Config options
| Field | Default | Notes |
|---|---|---|
| `api_key` | (required) | `sk-cp-...` style key from MiniMax |
| `region` | `global` | `cn` switches to `api.minimaxi.com` |
| `base_url` | | override either region's default |
| `max_tokens_default` | `4096` | used when `TurnRequest.MaxTokens` is unset |
## Architecture
- `internal/anthropic/` — minimal HTTP+SSE Anthropic Messages client
- `internal/translate/` — `canonical.TurnRequest` ↔ Anthropic Messages,
SSE Event → `canonical.TurnEvent` per-block state machine
- `cmd/plexum-minimax-provider-plugin/` — Plexum SDK ProviderPlugin entry
Both `text`, `thinking`, and `tool_use` content blocks round-trip
losslessly (signatures preserved for thinking blocks).
## License
Same as Plexum.