Reported issues for monitor
Pod holds 6 of 6 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to monitor.
Most discussed
MCP get_info tool ignores section parameter
Description: The get_info MCP tool accepts a section parameter (e.g. memory, clients), but this value is not passed through in the controller. The implementation calls client.getInfoParsed() without the section argument, causing all INFO sections to be returned regardless of input. Even invalid values are silently ignored.
How to reproduce: Call get_info({ section: 'memory' })
Expected behavior: Only the requested section (memory) should be returned
Actual behavior: All INFO sections are retu
Read the thread · 2026-05-07 · closed · outside contributor · 2 comments
feat(semantic-cache): runtime-configurable defaultTtl via __config hash
Background
The feature/cache-proposal-data-model---libs-support branch added periodic refresh of two Valkey hashes so that BetterDB Monitor proposals take effect without a process restart:
{name}:__config→SemanticCachethreshold (global + per-category){name}:__tool_policies→AgentCacheper-tool TTL
Both are now covered by the cache_propose_threshold_adjust and cache_propose_tool_ttl_adjust MCP tools.
Gap
SemanticCache.defaultTtl — how long stored entries live i
Read the thread · 2026-05-04 · closed · 2 comments
MCP server reports version 0.1.0 instead of 1.2.0
The McpServer instance in packages/mcp/src/index.ts:183 is hardcoded with version: '0.1.0', while the actual package version is 1.2.0. This causes MCP clients that rely on the server version to receive incorrect information.
File: packages/mcp/src/index.ts:183
Read the thread · 2026-05-07 · closed · outside contributor · 1 comment
MCP update
Review our MCP server for missing functionalities based on recent PRs and everything we've added since the last integration of commands in it.
Suggest new tools for it. We'll discuss them. Then implement them
Proposal: tools to add
The server exposes ~50 tools but has no coverage for several recently shipped features (AI observability, forecasting, inference latency, vector search, key analytics). Proposed additions, all read-only:
AI Observability (biggest gap)
- `ai_list_instan
Read the thread · 2026-07-22 · closed · 0 comments
MCP get_info tool ignores section parameter
The get_info MCP tool accepts a section parameter (e.g. memory, clients), but this value is not passed through in the controller. The implementation calls client.getInfoParsed() without the section argument, causing all INFO sections to be returned regardless of input. Even invalid values are silently ignored
How to reproduce: Call get_info({ section: 'memory' })
Expected behavior: Only the requested section (memory) should be returned
Actual behavior: All INFO sections are returned
Read the thread · 2026-05-07 · closed · outside contributor · 0 comments
HttpTelemetryAdapter: preserve existing Turso telemetry path
Parent PRD
PRD: Provider-Agnostic Telemetry Adapter with PostHog Support
What to build
Extract the current fetch() + 5s timeout fire-and-forget logic from UsageTelemetryService.sendEvent() into an HttpTelemetryAdapter that implements TelemetryPort. The factory returns this adapter when TELEMETRY_PROVIDER=http.
This is a thin wrapper — just the HTTP transport. identify() and shutdown() a
Read the thread · 2026-04-02 · closed · 0 comments
Most recent
The remaining reports are on the project's issue tracker.