Skip to content

feat: add private AI tracing with AgentPond - #32

Open
marcusschiesser wants to merge 1 commit into
moeadham:masterfrom
marcusschiesser:feat/agentpond-openinference
Open

feat: add private AI tracing with AgentPond#32
marcusschiesser wants to merge 1 commit into
moeadham:masterfrom
marcusschiesser:feat/agentpond-openinference

Conversation

@marcusschiesser

Copy link
Copy Markdown

Summary

  • initialize the AgentPond Firebase exporter through Firebase Functions onInit() after the default Admin app exists
  • register OpenInference's OpenAI instrumentation before the OpenRouter-backed client loads
  • redact forwarded-email prompts and generated calendar content while retaining model, token, latency, and error metadata
  • keep the AgentPond skills installed by npx agentpond@0.5.2 init

Why AgentPond

AgentPond makes fwd2cal's AI event extraction observable without adding a separate hosted tracing backend. Its OpenInference spans can show which model handled an email, how many tokens it used, how long extraction took, and whether a retry or structured-output failure occurred. That is especially useful for diagnosing emails that do not become valid calendar events. Trace batches stay in project-controlled Firebase Storage and can be synced for local DuckDB analysis.

Prompt and completion bodies are redacted by default because forwarded emails can contain personal or confidential information.

Verification

  • npm run lint
  • npm run build
  • npx tsc -p tsconfig.json --noEmit
  • loaded the compiled Functions entrypoint and completed the async AgentPond onInit() path with a synthetic Firebase config
  • exercised a real gpt-4o-mini request and observed an OpenInference LLM span with model and token metadata; input.value and output.value were both __REDACTED__

The repository's full test script was not run because it starts emulators, waits for an interactive Google OAuth login, and opens a browser. No deployment was performed.

Firebase Storage status

This repository does not currently configure Cloud Storage or Storage Rules in firebase.json, so this PR does not invent a rule override or claim that production access is verified. Before deployment, the project needs a configured default bucket and maintainer verification that no client rule can read or write agentpond/**. Live Firebase export, agentpond sync, and trace listing could not be verified without production bucket access.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant