PR #69699: fix(failover): classify MiniMax 529 high-traffic as overloaded

• Repository: openclaw/openclaw
• Author: Eruditi
• State: closed | merged: False
• Link: https://github.com/openclaw/openclaw/pull/69699

Description (problem / solution / changelog)

Fixes #69642

MiniMax returns HTTP 529 with the message "High traffic detected. For a more stable experience, upgrade to our Plus plan". The existing failover logic already maps status 529 to reason=overloaded in classifyFailoverReasonFromStatus(), but the text-based classifier isOverloadedErrorMessage() did not match this wording, so some code paths failed to trigger failover.

Fix: Add /high traffic detected.*upgrade to our plus plan/i to ERROR_PATTERNS.overloaded so that text-based classification also treats this as an overloaded signal.

This ensures that when MiniMax returns a 529 error, OpenClaw correctly classifies it as overloaded and triggers the configured fallback providers instead of surfacing the error directly to the user.

Changed files

• src/agents/pi-embedded-helpers/failover-matches.ts (modified, +4/-0)

PR #69728: fix(minimax): recognize MiniMax-M2.7 as VLM-capable model

• Repository: openclaw/openclaw
• Author: Eruditi
• State: closed | merged: False
• Link: https://github.com/openclaw/openclaw/pull/69728

Description (problem / solution / changelog)

Fixes #69648

MiniMax-M2.7 supports image understanding via the /v1/coding_plan/vlm endpoint, but isMinimaxVlmModel() only recognized MiniMax-VL-01. This caused M2.7 to be incorrectly routed to the generic anthropic-messages API path, producing:

Image model failed (minimax/MiniMax-M2.7): 400 {"type":"error","error":{"type":"invalid_request_error","message":"invalid params, chat content is empty (2013)"}}

Fix: Replace the hard-coded single-model check with a Set lookup that includes both MiniMax-VL-01 and MiniMax-M2.7.

Test coverage: Updated existing isMinimaxVlmModel test to assert both models are recognized and non-MiniMax providers are still rejected.

Changed files

• src/agents/minimax-vlm.normalizes-api-key.test.ts (modified, +4/-1)
• src/agents/minimax-vlm.ts (modified, +6/-1)