Query aggregate Langfuse cost, volume, latency, and model telemetry efficiently with Metrics API v2. Use for dashboards, rollout checks, usage summaries, and cost or latency comparisons; use Observations API v2 instead when individual rows are actually required.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Prefer one bounded GET /api/public/v2/metrics query over downloading and
aggregating observations. Metrics queries return aggregates and avoid exposing
prompt or output content.
Use scripts/query-metrics-v2.mjs:
node .codex/skills/langfuse-metrics/scripts/query-metrics-v2.mjs summary --from 2026-08-26T00:00:00Z --model-prefix gpt-5.6-
node .codex/skills/langfuse-metrics/scripts/query-metrics-v2.mjs cost-report --from 2026-08-26T00:00:00Z --to 2026-08-27T00:00:00Z --completed-meetings 12 --transcribed-minutes 347
node .codex/skills/langfuse-metrics/scripts/query-metrics-v2.mjs query --file query.json
The helper reads LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, and optional
LANGFUSE_BASE_URL (Chronote defaults to the US cloud host). summary makes a
single request grouped by provided model and observation name, returning count,
total cost, average latency, and p95 latency. Use --dry-run to inspect the
query without sending it. --model-prefix is sent as a Metrics v2 starts with filter so matching happens before the server's 1,000-row limit.
cost-report uses that same single aggregate query to return attributed cost,
cost by model and feature, known fully-unpriced model groups, and group-based
cost coverage. Pass PostHog's completed-meeting count and the application's
transcribed-minute denominator when available to add unit costs. Do not call
the coverage ratio exact: a group with some cost may still contain individual
unpriced observations. Keep any unpriced TTS, image, or provider activity
visible rather than estimating dollars from unrelated units.
Keep queries bounded with explicit UTC fromTimestamp and toTimestamp.
Start with the dimensions and metrics needed to answer the question; do not add
time buckets or high row limits speculatively. Metrics API v2 supports at most
1,000 rows and does not permit grouping by high-cardinality identifiers such as
trace, session, or user IDs.
Before interpreting an empty result as no traffic, check ingestion freshness. Data from Langfuse Python SDK versions before 4.7 or JS/TS versions before 5.4 can appear in v2 endpoints up to 15 minutes late.
If row-level investigation is necessary, use GET /api/public/v2/observations
with bounded fromStartTime and toStartTime, selective fields, and cursor
pagination. Do not use deprecated /api/public/observations or page-based
pagination. Omit the io field group unless the task genuinely requires user
content and that access is authorized.
On HTTP 429, honor Retry-After. The helper retries once only when the wait is
60 seconds or less; otherwise it stops and reports the wait. Do not work around
an organization-wide quota by rotating project keys. Langfuse applies rate
limits to organization-level resource buckets shared by its projects and keys.
Aggregate health does not prove output quality. Report routing/configuration, traffic, latency, cost, and error evidence separately from representative workload or human quality validation. This skill is read-only and does not authorize prompt, model-routing, evaluator, or production configuration writes.
Current official references:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Analyze Chronote product adoption with PostHog and Langfuse, including active users, meetings, feature usage, AI telemetry, and privacy-safe resolution of active Discord guild IDs to live server names.
The English summary is being prepared. Showing the original description.
Use when a change affects user-visible behavior at docs.chronote.gg and needs public documentation. Covers where docs live (apps/docs-site vs docs/), authoring checklist, yarn docs:check, and Algolia config. Trigger when the user mentions docs, release notes, what's-new, or user-facing PR changes.
The English summary is being prepared. Showing the original description.
Investigate errors, incidents, or product ideas using both internet research and repo-wide codebase research, then propose a concrete changeset plan with clarifying questions before any implementation. Use when a user asks to investigate, root-cause, or plan changes, or when an Issue or PR is referenced and needs a plan.
The English summary is being prepared. Showing the original description.
Configure and debug MCP servers for Claude Code, OpenCode, and Codex CLI, including auth headers, scope, and validation checks. Use when MCP tools fail to connect, when an MCP server returns 401/404/HTML, or when adding a new MCP server to this repo.
The English summary is being prepared. Showing the original description.
Configure and debug MCP servers for OpenCode, Codex CLI, and Claude Code, including auth headers, scope, and validation checks. Use when MCP tools fail to connect or when adding a new MCP server.
The English summary is being prepared. Showing the original description.
Use every time you push a commit to an active pull request, to verify the PR is truly stable before reporting merge readiness. Covers the post-push wait window, AI review audit (Copilot/Greptile/Codex), and the gh commands to snapshot PR state. Trigger on "I pushed" or "is the PR ready to merge".
The English summary is being prepared. Showing the original description.