openclaw - 💡(How to fix) Fix v2026.4.25 regression: memory-core breaks agent by using wrong API key for embeddings [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#73049Fetched 2026-04-28 06:28:13
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
Participants
Timeline (top)
cross-referenced ×1

Error Message

memory sync failed (search-bootstrap): Error: openai embeddings failed: 401 { "error": { "message": "Incorrect API key provided: sk-MjYxL...OTY=. You can find your API key at https://platform.openai.com/account/api-keys.", "type": "invalid_request_error", "code": "invalid_api_key" } }

Fix Action

Workaround

None found. The agent is completely blocked.

Code Example

memory sync failed (search-bootstrap): Error: openai embeddings failed: 401 {
  "error": {
    "message": "Incorrect API key provided: sk-MjYxL...OTY=. You can find your API key at https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}
RAW_BUFFERClick to expand / collapse

Bug Description

After upgrading from 2026.4.24 to 2026.4.25, the memory-core plugin breaks agent message processing by using the wrong API key for embeddings.

What changed

Before (2026.4.24): Agent used deepseek/deepseek-v4-pro via the deepseek provider at https://api.deepseek.com. Memory sync worked fine.

After (2026.4.25): Memory-core plugin now resolves embeddings API key from env.OPENAI_API_KEY instead of the deepseek provider key. This causes 401 errors that completely block the agent from processing any messages.

Error logs

memory sync failed (search-bootstrap): Error: openai embeddings failed: 401 {
  "error": {
    "message": "Incorrect API key provided: sk-MjYxL...OTY=. You can find your API key at https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Impact

  • Agent is completely non-functional after upgrade
  • QQ Bot receives messages but cannot generate responses
  • Memory subsystem blocks all message processing

Environment

  • OpenClaw: 2026.4.25 (aa36ee6)
  • Node: v22.17.1
  • Agent model: deepseek/deepseek-v4-pro
  • env.OPENAI_API_KEY: set (for scnet.cn proxy, NOT for deepseek)
  • env.OPENAI_BASE_URL: https://api.scnet.cn/api/llm/v1

Expected behavior

Memory-core should use the deepseek provider credentials for embeddings when the agent model is deepseek, not fall back to OPENAI_API_KEY from env.

Workaround

None found. The agent is completely blocked.

Additional context

This is a regression - the exact same config worked perfectly on 2026.4.24. The upgrade changed how memory-core resolves API keys.

extent analysis

TL;DR

Set the correct API key for the deepseek provider to fix the memory-core plugin issue.

Guidance

  • Verify that the deepseek provider key is correctly configured and not overridden by the env.OPENAI_API_KEY variable.
  • Check the memory-core plugin documentation to see if there are any configuration options to specify the API key for the deepseek provider.
  • Consider setting an environment variable specific to the deepseek provider to avoid conflicts with the OPENAI_API_KEY.
  • Review the upgrade notes for version 2026.4.25 to see if there are any specific instructions for configuring the memory-core plugin with the deepseek provider.

Example

No code snippet is provided as the issue is related to configuration and environment variables.

Notes

The issue is specific to the upgrade from 2026.4.24 to 2026.4.25, and the exact same configuration worked perfectly on the previous version. The memory-core plugin change to use the env.OPENAI_API_KEY instead of the deepseek provider key is the likely cause of the issue.

Recommendation

Apply a workaround by setting the correct API key for the deepseek provider, as the upgrade to version 2026.4.25 introduced a regression that breaks the memory-core plugin.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

Memory-core should use the deepseek provider credentials for embeddings when the agent model is deepseek, not fall back to OPENAI_API_KEY from env.

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix v2026.4.25 regression: memory-core breaks agent by using wrong API key for embeddings [1 participants]