#vector-store
Sorted by views, then solution_desc, solution, and root_cause length (desc).
2595 issues
When running the gateway with `gateway.bind=lan` inside Docker Desktop on macOS (Apple Silicon), the `openclaw-cli` container cannot connect to the gateway via WebSocket, making all CLI commands fail. This breaks the documented device pairing flow (`devices list` / `devices approve`).
OpenClaw `v2026.3.13` still appears to send an extremely large context window to Ollama (around `262144` / `265k`), even when a much lower context size is configured. This looks very similar to the previously reported issue about OpenClaw forcing or propagating an oversized context window to Ollama. Although that issue was marked as fixed, I can still reproduce the behavior on the latest version.
Environment | Component | Value | | ---------------- | ------------- | | OS | Windows 10/11 | | OpenClaw Version | 2026.4.1 | | Node.js | v25.7.0 | | Platform | win32 (x64) | ─── Description On Windows, even with security: standard and allowFrom configured, OpenClaw requires explicit approval for every command executed via Telegram. This makes remote management impractical. ─── Configuration { "security": "standard", "channels": { "telegram": { "enabled": true, "dmPolicy": "allowlist", "allowFrom": ["<telegram_user_id>"] } } } ─── Error Message Warning: allowlist auto-execution is unavailable on win32; explicit approval is required. Root Cause The restriction appears to be hardcoded: allowlist auto-execution is unavailable on win32; explicit approval is required ─── Impact • Remote management is impractical on Windows • Every command requires explicit approval • Telegram bot utility is severely limited ─── Suggested Fix
`openclaw plugins install` still blocks installation on dangerous-code findings even when `--dangerously-force-unsafe-install` is provided. Plugin Github: https://github.com/albertbuchard/forge
All CLI commands (cron, config, doctor, etc.) fail to connect to the gateway via WebSocket with handshake timeout. The gateway itself runs normally - channel messaging (Feishu) and browser dashboard both work. Only CLI-gateway RPC connections are broken.
qmd版本2.0.1，openclaw版本20260401.集成qmd后运行报错qmd boot update failed: Error: qmd update failed (code 1): file:///C:/software/nvm/v25.8.2/node_modules/@tobilu/qmd/bin/qmd:2 # Resolve symlinks so global installs (npm link / npm install -g) can find the ^
The `LiteAgent` concatenates retrieved memory content directly into the system prompt without sanitization. If memory entries have been poisoned (e.g., via indirect prompt injection through tool outputs), an attacker can inject arbitrary instructions into the system prompt of future agent interactions. **Severity**: MEDIUM **Rule**: AGENT-010 — Unsanitized External Content in Agent Prompt **OWASP Agentic Security Index**: ASI-01 — Prompt Injection **Affected files**: - `lib/crewai/src/crewai/lite_agent.py` (lines 568-581)
The `AGENTS.md` template bundled with CrewAI's project scaffolding (`crewai create`) includes a Calculator tool example that uses `eval()` on LLM-provided input, creating a remote code execution vulnerability in every new CrewAI project that follows the template. **Severity**: MEDIUM **Rule**: AGENT-053 — Unsafe Code Execution Pattern in Template **OWASP Agentic Security Index**: ASI-09 — Improper Output Handling **Affected files**: - `lib/crewai/src/crewai/cli/templates/AGENTS.md` (line 773)
When routing Azure GPT-5.2 chat requests through LiteLLM, `vector_store_ids` can leak into provider payload via `extra_body`, causing Azure to reject the request with: `litellm.BadRequestError: AzureException BadRequestError - Unknown parameter: 'vector_store_ids'`
When switching from a non-Anthropic model (e.g. MiniMax M2.7) to an Anthropic model (e.g. Claude Sonnet) mid-conversation, an orphaned \`tool_use\` block gets written to \`lcm.db\` without a corresponding \`tool_result\`. Every subsequent Anthropic API request for that channel then fails permanently with: \`\`\` LLM request rejected: messages.N: tool_use ids were found without tool_result blocks immediately after: <id>. Each tool_use block must have a corresponding tool_result block in the next message. \`\`\`