vercel/eve @vercel/agent-runs@1.0.0

on GitHub

Released 2026-11-15 · Compare with 0.0.4

Breaking Changes

• @vercel/agent-runs 1.0 puts its public API under semantic versioning, so it changes incompatibly only in a major release. (#5620)

Features

• Record an agent.approval span for every wait on a person, including questions, budget prompts, and connection sign-ins, not just tool approvals.
  agent.approval.kind is tool-approval, question, budget, or sign-in. A wait sits under the tool call it's about, or under the turn when no call owns it, and a sign-in names its connection in eve.connection.name. Instrumentation providers now receive sign-ins on interaction.opened and interaction.settled, with signIn.name naming the connection or tool; the sign-in URL and code stay out of the event. Questions and sign-ins from workflow tools such as ask_question now reach providers too, reported by the session that owns the tool call; a request a subagent asks is still reported once, by that session. @vercel/agent-runs adds TurnOperation.approval and findApproval, and an optional kind and connectionName on approvals. (#6004)
• Decision spans now name their turn and purpose, and record per-question results as gen_ai.decision.results when the trace records outputs.
  decision <model> spans carry agent.turn.id and agent.decision.purpose (model-selection, tool-approval, agent-routing, or custom), so Agent Runs can place a model-selection decision in a turn that is still running. Results follow the proposed OpenTelemetry GenAI decision conventions: choices, predicates, scores with their levels, and refusals, each keyed by the question's position. They are output content, recorded only when outputs are and dropped for any destination that declines outputs. AgentRun.decision accepts an optional purpose, and completing a decision with output records it as the results. (#6389)
• Add decision <model> OpenTelemetry spans for decide, automatic model selection, and tool approvals, with policy-aware model, usage, cost, and failure metadata that distinguishes refusals from request failures.
  A decision sits under the operation it runs in, or under the turn when model routing runs before the turn's first step. @vercel/agent-runs adds AgentRun.decision and an optional AgentTelemetry.activeSpan, so a decision nests under a host span inside its operation but not under a host span from another trace, such as a workflow step. (#5349)

Bug Fixes

• A context compaction's summary request during a turn now exports its own chat <model> span under the turn's invoke_agent span, with its token usage, cost, and ai.settings.context.eve.compaction.request=summary, so traces no longer undercount compacting turns.
  Model spans now also carry agent.turn.id. @vercel/agent-runs adds TurnOperation.modelCall for model calls a turn makes outside its steps.
  Thanks @zackleman for reporting this in #5922. (#6251)
• Name the memory store on memory provider tool calls, so a trace query by gen_ai.memory.store.id finds a scope's tool reads and writes as well as its recall and capture.
  The execute_tool span of a memory provider tool, such as profile__save, now carries gen_ai.memory.store.id and agent.memory.slot, matching the search_memory and upsert_memory spans of the same slot. The store ID is the slot's opaque scope key, so it is recorded whatever the trace policy captures. @vercel/agent-runs adds an optional memory lifecycle to ActiveOperation on tool operations to record it. (#6147)
• Fix durable agent traces keeping every finished turn that called tools in parallel: each one stayed in the session's serialized context, so step inputs grew with every turn.
  A checkpoint this process had already written, read back through another execution context, was treated as another process's write and forked the turn's trace tree; the stale copy then overwrote the tool completions and the checkpoint was never deleted. A replaced tree now also stops persisting. (#5835)
• Update eve's bundled dependencies, including the AI SDK, Vercel SDKs, Chat SDK, and MCP, to their latest releases, and OpenTelemetry to its latest 2.x releases.
  eve now requires ai 7.0.172 or later.
  YAML frontmatter, eval data files, and OpenAPI specs now parse with js-yaml 5 and YAML 1.2 values. An unquoted date such as 2024-01-02 loads as a string instead of a Date, and a 0b binary literal such as 0b101 loads as a string instead of a number. The YAML 1.1 tags !!timestamp, !!binary, !!set, !!omap, and !!pairs are no longer recognized, and a mapping with a non-scalar key, such as ? [a], throws. << merge keys still work.
  MCP connections over Streamable HTTP now fail when the server/discover request fails before the server answers, instead of retrying with initialize. Set protocolVersionDiscovery: false for a server that can't handle that request. Servers that answer server/discover with a JSON-RPC error or an HTTP error status other than 401 still use initialize, and servers that reject the protocol version with a supported legacy version still negotiate it. (#6378)
• Keep oversized checkpoints honest by preserving the real agent.trace.content.input/output capture flags and keeping the turn's copied input/output as a truncated copy (or omitting it) instead of rewriting the flags to false when a turn node exceeds the checkpoint size budget. (#5945)
• Raise the tracing content caps from 32 KiB per attribute and 64 KiB per checkpointed operation to 250 KiB and 512 KiB, so prompts up to 250 KiB are captured in full instead of truncated. (#5945)
• Make connection sign-ins countable in traces: each sign-in span names its agent, a failed sign-in records its reason, and a call a connection refused records which connection and why.
  agent.approval spans now carry gen_ai.agent.name and agent.name, so a query scoped to one agent no longer drops its sign-in prompts. A sign-in that fails with a reason code such as access_denied records it as agent.connection.authorization.reason; a sign-in that ends any other way, such as one a new message withdrew, records none. A tool call that fails with ConnectionAuthorizationFailedError, including one that never asked anyone to sign in, such as principal_required or sign_in_unavailable in a turn a schedule started, records eve.connection.name and agent.connection.authorization.reason on its execute_tool span. Only reason codes are recorded: a free-text reason or error message stays off the span whatever the trace policy records. (#6078)
• Store a turn's attributes once in its checkpoint.
  The turn's copy of the model input and output was also saved in the turn's data, which doubled that content in every checkpoint write and sent large prompts into the oversized-checkpoint fallback. Exported spans are unchanged. (#5949)