Skip to content

armgit / eve

Public Imported from GitHub
0

The Open Framework for Building Agents

Version Packages (#549)

github-actions[bot]39edcb19d2a3
diff --git a/.changeset/chat-sdk-channel-updates.md b/.changeset/chat-sdk-channel-updates.md
deleted file mode 100644
index 127c56a43..000000000
--- a/.changeset/chat-sdk-channel-updates.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": minor
----
-
-Expand the Chat SDK channel (`chatSdkChannel`): post completed assistant messages as markdown, stream replies via post-then-edit (configurable with `streaming` and `streamingEditIntervalMs`), surface typing status on turn start and tool calls, and degrade optional adapter operations (`startTyping`, `editMessage`) gracefully when an adapter does not implement them. Add the `messageToUserContent` inbound helper and export `isNotImplemented`. The default adapter webhook route is now `/eve/v1/{adapter}`.
diff --git a/.changeset/cool-camels-see.md b/.changeset/cool-camels-see.md
deleted file mode 100644
index 01ae3ddf2..000000000
--- a/.changeset/cool-camels-see.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": minor
----
-
-feat(eve): write skills into `$HOME/.agents/skills` instead of the workspace directory
diff --git a/.changeset/local-subagent-usage-results.md b/.changeset/local-subagent-usage-results.md
deleted file mode 100644
index 00dc3dd30..000000000
--- a/.changeset/local-subagent-usage-results.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Subagents now report their token usage back to the caller — local, runtime, and remote alike. A completed turn carries the session's token totals (`inputTokens`, `outputTokens`, `cacheReadTokens`, `cacheWriteTokens`) on its terminal result; remote agents transport the same totals over the session callback. The parent's turn emits one `invoke_agent` span per usage-bearing result (`gen_ai.operation.name=invoke_agent`, `gen_ai.agent.name`, `gen_ai.usage.*`, per the OpenTelemetry GenAI semantic conventions) in the caller's trace. Remote usage requires both sides to run this version; collection stays best-effort everywhere.
diff --git a/.changeset/message-received-attachments.md b/.changeset/message-received-attachments.md
deleted file mode 100644
index 9221f1351..000000000
--- a/.changeset/message-received-attachments.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-`message.received` events now include structured `parts` with text and file metadata so clients can render user attachments without parsing the flattened message summary. The default message reducer projects those attachments as `file` message parts while keeping raw bytes and internal sandbox paths off the stream.
diff --git a/.changeset/reintroduce-experimental-workflow.md b/.changeset/reintroduce-experimental-workflow.md
deleted file mode 100644
index d6a89fb3b..000000000
--- a/.changeset/reintroduce-experimental-workflow.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Reintroduce the `ExperimentalWorkflow` opt-in marker in `eve/tools`. Re-exporting it from `agent/tools/workflow.ts` enables the `Workflow` orchestration tool, which can spawn the agent's subagents from model-authored JavaScript. Workflow-spawned subagent calls are now capped per program by the new `limits.maxSubagents` agent setting (default 100) — calls beyond the budget resolve with a `WORKFLOW_SUBAGENT_LIMIT_REACHED` error result instead of starting a child session — and the tool stays root-only, so delegated subagent sessions never receive it.
diff --git a/.changeset/slack-markdown-file-posts.md b/.changeset/slack-markdown-file-posts.md
deleted file mode 100644
index 5c12f7551..000000000
--- a/.changeset/slack-markdown-file-posts.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Slack channel posts that combine Markdown and file uploads now send the Markdown message first and upload files as a threaded follow-up. This preserves Slack's full Markdown rendering, including tables, instead of downgrading the response into a file upload comment.
diff --git a/.changeset/spicy-hounds-pause.md b/.changeset/spicy-hounds-pause.md
deleted file mode 100644
index cfd7062f3..000000000
--- a/.changeset/spicy-hounds-pause.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Reaching a session token limit no longer fails interactive sessions outright. The harness now pauses and sends a deterministic HITL continuation prompt; answering "Continue" grants a fresh budget window of the configured size, while "Stop" ends the session gracefully with `session.completed`. Task-mode sessions keep the structured `SESSION_TOKEN_LIMIT_REACHED` failure so parent tool calls receive an error result.
diff --git a/.changeset/subagent-quota-inheritance.md b/.changeset/subagent-quota-inheritance.md
deleted file mode 100644
index ca29ea89c..000000000
--- a/.changeset/subagent-quota-inheritance.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Delegated subagent sessions now receive a share of the parent's remaining token quota at dispatch time — the remainder split across the batch's delegated calls — instead of a fixed 5M input-token cap, and a completed child's usage counts against the parent's quota, so a delegation tree can never outspend the budget configured at its root. Session token limits also accept `false` to uncap a session explicitly. Delegated children likewise inherit the parent's delegation caps (`limits.maxSubagentDepth` and `limits.maxSubagents`); on every inherited axis the tighter of the configured and inherited value wins.
diff --git a/packages/eve/CHANGELOG.md b/packages/eve/CHANGELOG.md
index 268762762..1c0860bbc 100644
--- a/packages/eve/CHANGELOG.md
+++ b/packages/eve/CHANGELOG.md
@@ -1,5 +1,21 @@
# eve
+## 0.21.0
+
+### Minor Changes
+
+- 79e9959: Expand the Chat SDK channel (`chatSdkChannel`): post completed assistant messages as markdown, stream replies via post-then-edit (configurable with `streaming` and `streamingEditIntervalMs`), surface typing status on turn start and tool calls, and degrade optional adapter operations (`startTyping`, `editMessage`) gracefully when an adapter does not implement them. Add the `messageToUserContent` inbound helper and export `isNotImplemented`. The default adapter webhook route is now `/eve/v1/{adapter}`.
+- 73a9bf9: feat(eve): write skills into `$HOME/.agents/skills` instead of the workspace directory
+
+### Patch Changes
+
+- 99c2380: Subagents now report their token usage back to the caller — local, runtime, and remote alike. A completed turn carries the session's token totals (`inputTokens`, `outputTokens`, `cacheReadTokens`, `cacheWriteTokens`) on its terminal result; remote agents transport the same totals over the session callback. The parent's turn emits one `invoke_agent` span per usage-bearing result (`gen_ai.operation.name=invoke_agent`, `gen_ai.agent.name`, `gen_ai.usage.*`, per the OpenTelemetry GenAI semantic conventions) in the caller's trace. Remote usage requires both sides to run this version; collection stays best-effort everywhere.
+- c5cddb6: `message.received` events now include structured `parts` with text and file metadata so clients can render user attachments without parsing the flattened message summary. The default message reducer projects those attachments as `file` message parts while keeping raw bytes and internal sandbox paths off the stream.
+- 5ef4ec6: Reintroduce the `ExperimentalWorkflow` opt-in marker in `eve/tools`. Re-exporting it from `agent/tools/workflow.ts` enables the `Workflow` orchestration tool, which can spawn the agent's subagents from model-authored JavaScript. Workflow-spawned subagent calls are now capped per program by the new `limits.maxSubagents` agent setting (default 100) — calls beyond the budget resolve with a `WORKFLOW_SUBAGENT_LIMIT_REACHED` error result instead of starting a child session — and the tool stays root-only, so delegated subagent sessions never receive it.
+- 61745d5: Slack channel posts that combine Markdown and file uploads now send the Markdown message first and upload files as a threaded follow-up. This preserves Slack's full Markdown rendering, including tables, instead of downgrading the response into a file upload comment.
+- d408d0b: Reaching a session token limit no longer fails interactive sessions outright. The harness now pauses and sends a deterministic HITL continuation prompt; answering "Continue" grants a fresh budget window of the configured size, while "Stop" ends the session gracefully with `session.completed`. Task-mode sessions keep the structured `SESSION_TOKEN_LIMIT_REACHED` failure so parent tool calls receive an error result.
+- da2ec6c: Delegated subagent sessions now receive a share of the parent's remaining token quota at dispatch time — the remainder split across the batch's delegated calls — instead of a fixed 5M input-token cap, and a completed child's usage counts against the parent's quota, so a delegation tree can never outspend the budget configured at its root. Session token limits also accept `false` to uncap a session explicitly. Delegated children likewise inherit the parent's delegation caps (`limits.maxSubagentDepth` and `limits.maxSubagents`); on every inherited axis the tighter of the configured and inherited value wins.
+
## 0.20.0
### Minor Changes
diff --git a/packages/eve/package.json b/packages/eve/package.json
index ee43003d2..6e4ac8cbe 100644
--- a/packages/eve/package.json
+++ b/packages/eve/package.json
@@ -1,6 +1,6 @@
{
"name": "eve",
- "version": "0.20.0",
+ "version": "0.21.0",
"private": false,
"description": "Filesystem-first framework for durable backend AI agents that run anywhere.",
"keywords": [