The Open Framework for Building Agents
Version Packages (#4717)
github-actions[bot]de7a408e4dc5
diff --git a/.changeset/clean-agent-tracing.md b/.changeset/clean-agent-tracing.mddeleted file mode 100644index a7a5ab6de..000000000--- a/.changeset/clean-agent-tracing.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------eve's agent spans now come from the shared tracing library, and durable turns recover from one checkpoint per turn. Each tool call is still one `execute_tool` span, a local subagent's first turn still nests under its caller, and trace schema version 4 is unchanged.diff --git a/.changeset/connection-tool-annotations.md b/.changeset/connection-tool-annotations.mddeleted file mode 100644index fd462e7eb..000000000--- a/.changeset/connection-tool-annotations.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Connection approval policies now receive `toolAnnotations`, the hints an MCP server declared for the called tool (such as `readOnlyHint` and `destructiveHint`), so a policy can skip approval for read-only tools. It is `undefined` when the server declares none.diff --git a/.changeset/custom-approval-prompts.md b/.changeset/custom-approval-prompts.mddeleted file mode 100644index 734afba0c..000000000--- a/.changeset/custom-approval-prompts.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Tools can now define `approval.prompt` to show a human-readable, input-aware summary in approval requests. Slack keeps the complete tool input available in a collapsed block below the approval card.diff --git a/.changeset/eval-scores-and-verdicts.md b/.changeset/eval-scores-and-verdicts.mddeleted file mode 100644index 481e4f8fc..000000000--- a/.changeset/eval-scores-and-verdicts.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": minor------Adds `t.score(evaluation)` for recording a score from 0 to 1, named with `.label(key)` and gated with `.gate()` or `.atLeast()`. `AssertionResult` gains `key`, and `score`, `threshold`, and `passed` are now optional: `score` is absent when the scorer threw, and `threshold` and `passed` are absent when no rule applies, so custom reporters should treat `passed === false` as the failure signal. `eve eval` warns when soft assertions in one eval share a name with different scores.diff --git a/.changeset/quiet-agent-traces.md b/.changeset/quiet-agent-traces.mddeleted file mode 100644index ef57d6cc1..000000000--- a/.changeset/quiet-agent-traces.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Extract reusable agent tracing with wrapped execution, model stream completion, remote delegation, and durable turns that save and resume themselves through a checkpointer. Preserve trace schema version 4 while sharing one span lifecycle with eve.diff --git a/.changeset/schema4-tool-names.md b/.changeset/schema4-tool-names.mddeleted file mode 100644index 1dd8de017..000000000--- a/.changeset/schema4-tool-names.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------The agent tracing library now writes schema 4's `agent.action.kind`, `agent.action.name`, and `agent.action.outcome` on tool and approval spans itself, so hosts other than eve render correctly in Agent Runs. eve's trace output is unchanged.diff --git a/packages/eve/CHANGELOG.md b/packages/eve/CHANGELOG.mdindex 89c704248..1e243e475 100644--- a/packages/eve/CHANGELOG.md+++ b/packages/eve/CHANGELOG.md@@ -1,5 +1,19 @@# eve+## 0.79.0++### Minor Changes++- bc2be45: Adds `t.score(evaluation)` for recording a score from 0 to 1, named with `.label(key)` and gated with `.gate()` or `.atLeast()`. `AssertionResult` gains `key`, and `score`, `threshold`, and `passed` are now optional: `score` is absent when the scorer threw, and `threshold` and `passed` are absent when no rule applies, so custom reporters should treat `passed === false` as the failure signal. `eve eval` warns when soft assertions in one eval share a name with different scores.++### Patch Changes++- 76f6854: eve's agent spans now come from the shared tracing library, and durable turns recover from one checkpoint per turn. Each tool call is still one `execute_tool` span, a local subagent's first turn still nests under its caller, and trace schema version 4 is unchanged.+- f5e5183: Connection approval policies now receive `toolAnnotations`, the hints an MCP server declared for the called tool (such as `readOnlyHint` and `destructiveHint`), so a policy can skip approval for read-only tools. It is `undefined` when the server declares none.+- 302a4d3: Tools can now define `approval.prompt` to show a human-readable, input-aware summary in approval requests. Slack keeps the complete tool input available in a collapsed block below the approval card.+- 422b628: Extract reusable agent tracing with wrapped execution, model stream completion, remote delegation, and durable turns that save and resume themselves through a checkpointer. Preserve trace schema version 4 while sharing one span lifecycle with eve.+- 485d0f5: The agent tracing library now writes schema 4's `agent.action.kind`, `agent.action.name`, and `agent.action.outcome` on tool and approval spans itself, so hosts other than eve render correctly in Agent Runs. eve's trace output is unchanged.+## 0.78.0### Minor Changesdiff --git a/packages/eve/package.json b/packages/eve/package.jsonindex 24a64cef7..b7f0c23a0 100644--- a/packages/eve/package.json+++ b/packages/eve/package.json@@ -1,6 +1,6 @@{"name": "eve",- "version": "0.78.0",+ "version": "0.79.0","private": false,"description": "Filesystem-first framework for durable backend AI agents that run anywhere.","keywords": [