feat(minimax): add MiniMax M3 model with 1M context window#1470
Merged
Conversation
M3 is MiniMax's next-gen flagship with coding/agentic capabilities, 1M token context (1,048,576), and benchmark performance on par with Opus 4.7 on SWE-bench. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
The integrations/models/minimax.ts was missing the minimax-m3 model definition that was added to the vendor config. This caused the model picker to not show MiniMax M3 as a selectable option despite it being present in the picker list. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
|
The free model id |
jatmn
requested changes
Jun 1, 2026
jatmn
left a comment
jatmn
left a comment
Collaborator
There was a problem hiding this comment.
Thanks for the contribution. I do not see any code-level issues in the changed MiniMax model registration, but this is not merge-ready yet because the branch is currently blocked from merging.
Please rebase/update the branch onto the latest main and rerun the required checks so the PR can merge cleanly.
When a MiniMax provider profile was active, the /model picker collapsed to the single model pinned in the profile (e.g. MiniMax-M2.7), hiding the rest of the catalog — including M3. mergeActiveProfileModelOptions now surfaces the complete catalog for native vendor routes (which ship a curated static catalog), while gateways keep the profile model list as a whitelist. Added isNativeVendorCatalogRoute() to draw that distinction. Also harden isMiniMaxProvider() to detect the MiniMax host on ANTHROPIC_BASE_URL (anthropic-proxy transport), not just OPENAI_BASE_URL, and switch the vendor defaultModel to MiniMax-M3. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
Collaborator
|
@kevincodex1 still failing smoke. |
These tests passed individually but failed under `bun test` because bun does not unregister mock.module() overrides on mock.restore(), so stubs leaked into later files. Root-caused and fixed each leak at the source: - providerFallback: inject settings/profiles into getProviderFallbackChain and resolveNextFallbackProviderFromState; the test now uses DI instead of mock.module on settings.js/providerProfiles.js (fixed 7 attribution fails). - apiPreconnect: accept an injected apiProvider (defaults to getAPIProvider); the test passes it explicitly so a leaked providers.js mock can't force 'firstParty' (fixed 3 preconnect fails). - preflightChecks: build a COMPLETE axios stub (defaults + interceptors) and re-register the real module in afterEach, so the partial stub no longer breaks proxy.ts's axios.defaults usage in tests/sdk/query-lifecycle (fixed 2 query-resume fails). - flagSettings: realpath the temp dir so the macOS /tmp -> /private/tmp symlink doesn't mismatch the canonicalised --settings path (fixed 1 fail). Full suite now green: 3343 pass / 0 fail under both `bun test` and `bun test --max-concurrency=1`. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
jatmn
requested changes
Jun 1, 2026
jatmn
left a comment
jatmn
left a comment
Collaborator
There was a problem hiding this comment.
I found an issue that needs to be addressed before this is ready.
Findings
- [P2] Keep env-only MiniMax defaults on M3
src/utils/model/model.ts:395
This PR changes the MiniMax descriptor/default profile path toMiniMax-M3, but the runtime fallback used when a user only hasMINIMAX_API_KEY/MiniMax base-url env configured still returnsMiniMax-M2.7when no explicit model env is present. That means the same provider can default to M3 when selected through--provider minimaxor a saved profile, but silently stay on M2.7 for env-only MiniMax sessions, so part of the advertised default-model update is not actually applied. Please update the MiniMax fallback defaults in the model helpers, and the adjacent regression test that still asserts the old M2.7 default, so all MiniMax entry points agree on M3 unless the user pins another model.
The descriptor/profile path and --provider minimax already default to MiniMax-M3, but getDefaultMainLoopModelSetting() still fell back to MiniMax-M2.7 for env-only sessions (only MINIMAX_API_KEY / a MiniMax base URL set, no explicit model env). That left part of the default-model update unapplied. Align the env-only fallback (and the dead applyProviderFlag fallback) on M3, and update the regression test accordingly. Users who pin a model via env/profile are unaffected. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
jatmn
approved these changes
Jun 1, 2026
jatmn
left a comment
jatmn
left a comment
Collaborator
There was a problem hiding this comment.
Thanks for the update. I rechecked the previously discussed paths and do not see any remaining actionable issues from my side.
hotmanxp
added a commit
to hotmanxp/openclaude
that referenced
this pull request
Jun 2, 2026
Align vendor profile default with upstream M3 release (Gitlawb#1470). - defaultModel: 'MiniMax-M2.7' → 'MiniMax-M3' - M3 model definition in integrations/models/minimax.ts already 1:1 with upstream Users with explicit OPENAI_MODEL env or pinned profile are unaffected.
6 tasks
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
3 participants
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.
M3 is MiniMax's next-gen flagship with coding/agentic capabilities, 1M token context (1,048,576), and benchmark performance on par with Opus 4.7 on SWE-bench.