---
type: "post"
id: "see-every-agent-session-in-ai-gateway-logs-2243ee"
slug: "see-every-agent-session-in-ai-gateway-logs-2243ee"
title: "See every agent session in AI Gateway logs."
description: "Vercel’s Sessions view changes the unit of inspection in AI Gateway logs from isolated requests to multi-turn agent sessions."
retrieval_nugget: "Vercel’s Sessions view changes the unit of inspection in AI Gateway logs from isolated requests to multi-turn agent sessions."
published_at: "2026-10-18"
updated_at: "2026-10-18"
record_date: "2026-10-18"
date_kind: "published_at"
topics: ["agent-observability","observability","agents"]
source_urls: ["https://vercel.com/changelog/ai-gateway-logs-now-show-session-affinity"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:see-every-agent-session-in-ai-gateway-logs-2243ee"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:5ad0f1b50684a297f01fe2cc83b1898284e866effd61ad29744bda4dc2f72f5d","reviewed_at":"2026-10-18T20:03:11.856Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Session-level observability can make the relationship between provider routing, prompt caching, and spend inspectable, even though it does not itself prove savings.","observed_facts":[{"text":"The Sessions view groups requests and shows the coding agent or app, cost, models, providers, and cached-input share across turns.","source_urls":["https://vercel.com/changelog/ai-gateway-logs-now-show-session-affinity"]},{"text":"Opening a session shows cache hit rate, duration, and a turn-by-turn path with model, timing, and provider.","source_urls":["https://vercel.com/changelog/ai-gateway-logs-now-show-session-affinity"]},{"text":"Session affinity routes each turn to the provider that served the prior turn; users can also supply a repeated sessionId or x-session-id.","source_urls":["https://vercel.com/changelog/ai-gateway-logs-now-show-session-affinity"]}],"mechanism":"Grouping turns into sessions exposes provider continuity and cache behavior alongside cost; affinity keeps successive turns on the preceding provider, where more prompt content may be cached.","why_now":"Multi-turn coding and chat agents make individual request logs a poor unit for understanding provider continuity and accumulated cost.","implications":["Teams using AI Gateway can inspect session-level routing and cache behavior without reconstructing conversations from scattered requests."],"evidence_boundary":"The source is a product changelog describing fields and behavior; it offers no independent performance measurements, before-and-after cost data, or evidence that affinity improves every workload.","watch_conditions":["Whether teams can show lower per-session cost or latency while preserving routing reliability."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific session-logging release; this records the distinct observability change without asserting a link to an earlier record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/see-every-agent-session-in-ai-gateway-logs-2243ee/","markdown":"https://newruntime.com/posts/see-every-agent-session-in-ai-gateway-logs-2243ee.md","json":"https://newruntime.com/posts/see-every-agent-session-in-ai-gateway-logs-2243ee.json"}
related_patterns: ["runtime-observability-becomes-the-primary-engineering-focus-for-ai"]
---

# See every agent session in AI Gateway logs.

## Retrieval answer

Vercel’s Sessions view changes the unit of inspection in AI Gateway logs from isolated requests to multi-turn agent sessions.

Vercel’s Sessions view changes the unit of inspection in AI Gateway logs from isolated requests to multi-turn agent sessions. Session-level observability can make the relationship between provider routing, prompt caching, and spend inspectable, even though it does not itself prove savings.

The mechanism is: Grouping turns into sessions exposes provider continuity and cache behavior alongside cost; affinity keeps successive turns on the preceding provider, where more prompt content may be cached. The log view then presents a session’s duration, cache hit rate, and turn-by-turn path. Multi-turn coding and chat agents make individual request logs a poor unit for understanding provider continuity and accumulated cost.

The source confirms the feature’s described fields and behavior, but provides no independent performance measurements, before-and-after cost data, or evidence that affinity improves outcomes for every workload. The evidence boundary is: The source is a product changelog describing fields and behavior; it offers no independent performance measurements, before-and-after cost data, or evidence that affinity improves every workload. Teams using AI Gateway can inspect session-level routing and cache behavior without reconstructing conversations from scattered requests. Whether teams can show lower per-session cost or latency while preserving routing reliability. This is a distinct analytical record because no prior New Runtime record is supplied for this specific session-logging release.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Observability](https://newruntime.com/topics/agent-observability.md): Explore the agent-observability topic hub.
- topic hub: [Observability](https://newruntime.com/topics/observability.md): Explore the observability topic hub.
- topic hub: [Agents](https://newruntime.com/topics/agents.md): Explore the agents topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)