Repository navigation
Conversation
…cks and defaults Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
🤖 Open Code ReviewTarget: PR #2555 🔍 OpenCodeReview found 6 issue(s) in this PR.
1.
|
|
…cks and defaults Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
🤖 Open Code ReviewTarget: PR #2555 🔍 OpenCodeReview found 6 issue(s) in this PR.
1.
|
|
Description
Anthropic retired
claude-3-haiku-20240307on April 20, 2026 (model deprecations), so requests to it now fail. A few places in MemOS still hardcode it:api-key:validateandapi-key:validate-providerinhandlers.ts): the check sends a message toclaude-3-haiku-20240307and treats any non-OK reply as a bad key. Since the model is gone, every valid Anthropic key is rejected and users can't get past setup.shared/llm-call.tsandingest/providers/anthropic.ts, in bothpackages/memos-coreandapps/memos-local-openclaw): withprovider: anthropicand nomodelset, every summarize/topic/dedup call fails.viewer/server.ts, both copies): with no model entered, the test always fails.What changed:
GET https://api.anthropic.com/v1/modelsinstead of sending a message, the same way the OpenAI check already works. It still returns 401 for a bad key, costs no tokens, and won't break again when the next model retires.claude-haiku-4-5-20251001, Anthropic's listed replacement for Haiku 3. It still accepts thetemperaturethese calls send.api-key:validateunit test to check the new endpoint and added one forapi-key:validate-providerwithanthropic.Bedrock defaults (
anthropic.claude-3-haiku-20240307-v1:0) are untouched: Bedrock has its own retirement schedule.There's no issue for this one; I found it while reading the code.
Type of change
How Has This Been Tested?
I haven't run the test suite or the app locally. The changes are a model ID swap and an endpoint swap for the key check, plus the unit tests above. CI should cover them.
🤖 Generated with Claude Code