feat: upgrade MiniMax default model to M3#328
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Add MiniMax provider with M3 as the default model (512K context, 128K max output, image input support) - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Configure agent defaults (simple, primary_agent, assistant, generator, etc.) on M3 - Register MiniMax provider type, env vars (MINIMAX_API_KEY, MINIMAX_SERVER_URL, MINIMAX_PROVIDER) - Add unit tests covering config loading, models list, prefix behavior, and missing API key
6 tasks
sirozha
pushed a commit
that referenced
this pull request
Jun 18, 2026
Issue #321 requests a native Vertex AI provider with service-account / ADC auth, opened after #310 clarified Vertex is not supported today. The issue carries a full implementation outline and four open questions, and the author asks for direction on adapter strategy and Gemini-vs-Claude scope before implementing. Add examples/proposals/vertex_ai_provider.md, a planning RFC that frames the work before any code is written: - Distinguishes the current options (AI Studio gemini, direct Anthropic, AWS Bedrock, and the custom OpenAI-compatible LiteLLM proxy workaround) from the proposed native vertex provider. - Recommends a staged approach: v1 Gemini-on-Vertex with ADC / service-account auth; Claude-on-Vertex deferred to a maintainer decision, noting it likely belongs on the Anthropic adapter (Vertex auth/endpoint mode) rather than the Gemini-shaped path because the message schema differs. - Models auth on the existing Bedrock multi-auth precedent (ADC default chain plus service-account file), and flags that service-account JSON is sensitive and must be file-mounted/secret-managed, never pasted into UI or logs. - Captures config/migration touch points (provider checklist, REST Valid() whitelist, PROVIDER_TYPE enum-swap migration) so the eventual implementation size is clear, and restates the issue's open questions. Docs/RFC only. No code, schema, migration, generated, frontend, or provider runtime files are touched, and no new env vars or types are added; every VERTEX_* key and type named is labeled as a candidate. No overlap with the provider files in open PR #328.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add MiniMax provider to PentAGI with MiniMax-M3 as the default model, keeping MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives.
Changes
MiniMaxprovider package (backend/pkg/providers/minimax/) implementing theprovider.Providerinterface via the OpenAI-compatiblehttps://api.minimax.io/v1endpoint.ProviderMiniMaxtype,DefaultProviderNameMiniMaxname, and wire the provider intoNewProviderController/NewProvider/buildProviderFromConfig/buildProviderFromConfig/GetProviderpaths.MINIMAX_API_KEY,MINIMAX_SERVER_URL(defaulthttps://api.minimax.io/v1),MINIMAX_PROVIDERand the matching secret pattern.provider.ProviderMiniMaxto theValid()whitelist inpkg/server/models/providers.go(required for REST API acceptance).M3first, no legacyM1/M2/M2.1/M2.5), model prefix behaviour, and missing-API-key error.Why
MiniMax-M3 is MiniMax's latest flagship model (512K context, 128K max output, image input support) and is the right default for a security-testing workload that benefits from large context and multimodal input. MiniMax-M2.7 and its high-speed variant are retained for users who want to pin to the previous generation.
Model list
MiniMax-M3(default) — 512K context, 128K output, image input, input $0.60 / output $2.40 per 1M tokensMiniMax-M2.7— input $0.40 / output $1.10MiniMax-M2.7-highspeed— input $0.40 / output $1.10No legacy models (
MiniMax-M1/MiniMax-M2/MiniMax-M2.1/MiniMax-M2.5) are included.API docs
Testing
go test ./pkg/providers/minimax/...— 7/7 passing (config loading, provider type, models list with M3 as first entry, prefix behaviour, missing key, usage extraction).go build ./pkg/providers/minimax/...— clean.