Skip to content

armgit / eve

Public Imported from GitHub
0

The Open Framework for Building Agents

Version Packages (#4560)

github-actions[bot]0ac209c2be33
diff --git a/.changeset/accept-protocol-1-remotes.md b/.changeset/accept-protocol-1-remotes.md
deleted file mode 100644
index b914737c1..000000000
--- a/.changeset/accept-protocol-1-remotes.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Accept create-session responses from remote agents on eve 0.66–0.68 (protocol 1). A newer parent no longer fails a call that the older remote already accepted and is running.
diff --git a/.changeset/catalog-call-labels.md b/.changeset/catalog-call-labels.md
deleted file mode 100644
index 1db415fd5..000000000
--- a/.changeset/catalog-call-labels.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Catalog calls now read as what happened: `eve__search` shows `Search tools for “linear issues”` and then how much it found, a skill load shows `Load skill <name>` and then `Loaded skill <name>`, and a connection's sign-in entry shows `Sign in to Linear`. Linear activities, Chat SDK typing indicators, and ACP tool calls now show each call's label instead of its raw tool name, and `eve/client` tool parts carry that text as `toolMetadata.eve.label`.
diff --git a/.changeset/deferred-skills.md b/.changeset/deferred-skills.md
deleted file mode 100644
index 4b3fb4a3e..000000000
--- a/.changeset/deferred-skills.md
+++ /dev/null
@@ -1,10 +0,0 @@
----
-"eve": minor
----
-
-Skills now load through `eve__skill({ name })`, which every agent with a skill has in place of `load_skill`, and a skill with `deferred: true` (in `SKILL.md` frontmatter or on `defineSkill`, static or dynamic) leaves the system prompt and is found with `eve__search` instead.
-
-- The `load_skill` tool and the `eve/tools/load_skill` export are removed. Delete any `agent/tools/load_skill.ts` override or approval policy that names it; an authored `agent/tools/load_skill.ts` is now an ordinary tool.
-- A skill load's `load-skill` action now carries the skill's `name`, and its `input` is the model's `{ name }` instead of `{ skill }`. Its result is a `load-skill-result` with the same `name` instead of a `tool-result` named `load_skill`. Its client message part has the `toolName` `eve__skill` instead of `eve:load-skill`, with the skill's name in `toolMetadata.eve.name`. Sessions recorded by earlier versions replay with `name` filled in from `input.skill`.
-- Eval facts report skill loads in `skillLoads`, which `t.loadedSkill` reads. They no longer count toward `toolCallCount`, `usedNoTools`, or `maxToolCalls`.
-- Skill names must use only ASCII letters, digits, underscores, and dashes, start with a letter or digit, and have at most 64 characters. The compiler rejects a static skill with another name, and eve skips a dynamic skill resolver that returns one.
diff --git a/.changeset/deferred-tools-catalog.md b/.changeset/deferred-tools-catalog.md
deleted file mode 100644
index a11b5f53b..000000000
--- a/.changeset/deferred-tools-catalog.md
+++ /dev/null
@@ -1,16 +0,0 @@
----
-"eve": minor
----
-
-An agent with deferred entries or connections now has `eve__search` to find tools marked `deferred: true`, agents marked `tool: "deferred"`, and every connection tool, and `eve__tool` to call them, without growing the model's tool list. An agent with skills has `eve__skill` to load them, and `eve__search` also finds deferred skills. An agent with none of these gets no catalog tools, so its tool list is unchanged apart from `load_skill` becoming `eve__skill`. They replace `connection_search` and `connection_execute`, and stream events, approvals, hooks, and traces now name each connection tool call `<connection>__<tool>`. `eve__search` never asks the user to sign in: it lists a connection that needs sign-in under the connection's own name, and `eve__tool` on that name, such as `eve__tool({ name: "linear" })`, asks the user to sign in. `eve__search` takes a required `query`; a query such as `linear__` searches only that connection's tools.
-
-Breaking changes:
-
-- The tools eve adds itself now live in the `eve` namespace: `task_wait` is `eve__task_wait`, `task_cancel` is `eve__task_cancel`, and `final_output`, the tool a session with an output schema calls to deliver its structured result, is `eve__reply`. The catalog tools are `eve__search`, `eve__tool`, and `eve__skill`. Update evals, approval policies, hooks, and channel code that match `task_wait`, `task_cancel`, or `final_output` by name. A turn held on `task_wait` when you upgrade stays held until the next message or a cancel.
-- eve reserves the `eve` namespace. A tool, subagent, skill, connection, or extension mount named `eve` or starting with `eve__` now fails to build, or fails when the agent loads or a dynamic entry resolves; rename it. `search`, `execute`, `task_wait`, `task_cancel`, and `final_output` are ordinary names again.
-- A connection owns its name and every name starting with `<name>__`. A tool, subagent, or connection under another connection's prefix is rejected at build time, and a dynamic one when it resolves.
-- Dynamic tool map keys must be legal tool names: ASCII letters, digits, `_`, and `-`, starting with a letter, up to 64 characters.
-- Connection approvals are keyed by `<connection>__<tool>` instead of a `[connection, tool]` pair, so saved "always approve" decisions for connection tools reset.
-- A `connection_execute` call still waiting for approval when you upgrade fails when someone answers it, with "The tool "connection_execute" is no longer available, so the call didn't run."
-- Eval tool-name helpers (`calledTool`, `notCalledTool`, `toolOrder`, and `requireToolCall`) now throw, saying what to assert instead, for `eve__tool` and `eve__skill`, whose calls are reported under the entry they reach and as skill loads, and for a retired eve tool name (`load_skill`, `task_wait`, `task_cancel`, `final_output`, `connection_search`, `connection_execute`) unless the root agent declares a tool by that name or has a dynamic tool resolver. Before, `notCalledTool` on one of these names always passed. `usedNoTools` and `maxToolCalls` count `eve__search` calls; skill loads no longer do.
-- Removed: the `parentCallId` field on `tool-call` actions in `actions.requested` events, and the `agent.action.parent_call_id` span attribute. The subagent `parentCallId` on `session.started` invocation metadata is unchanged.
diff --git a/.changeset/eve-code-workspace-roots.md b/.changeset/eve-code-workspace-roots.md
deleted file mode 100644
index c4b9d6237..000000000
--- a/.changeset/eve-code-workspace-roots.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-`grep` and `apply_patch` in `eve/extensions/code` now work in sandboxes whose workspace is not `/workspace`, such as `/app`. `apply_patch` no longer requires a git checkout: `root` is optional and defaults to the workspace root, and outside git it still reports whitespace problems the patch introduced. It also accepts unified-diff range headers such as `@@ -118,8 +118,8 @@ def second():`, using the function context to pick between identical blocks.
diff --git a/.changeset/eve-git-extension.md b/.changeset/eve-git-extension.md
deleted file mode 100644
index 5cd14b10e..000000000
--- a/.changeset/eve-git-extension.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"eve": minor
----
-
-GitHub work moves out of `eve/extensions/code` into a new built-in extension, `eve/extensions/git`. The code extension used to tell every agent that "GitHub credentials are not available to ordinary `bash`" and to route GitHub work through its `gh` tool, which only works with Connect-brokered `github` config. Agents whose shell already has `gh` credentials were steered to a tool that could not authenticate.
-
-`git({})` adds the GitHub instructions and a `git__pr` skill that commits, pushes, and opens a draft with the shell's `gh pr create --draft`. `git({ github })` adds the Connect-brokered `git__gh` tool and switches `git__pr` to the signed-commit workflow. The tool and sandbox helpers are exported from `eve/extensions/git/tools` and `eve/extensions/git/sandbox`.
-
-Deprecated: `code({ github })`. While it is set, the code extension still contributes `code__gh`, its GitHub instructions, and the signed-commit `code__pr` skill. Without it, `code({})` no longer contributes `code__gh`, `code__pr`, or any GitHub instructions; mount `eve/extensions/git` for the pull request skill. `gh` from `eve/extensions/code/tools` and the GitHub shell helpers from `eve/extensions/code/sandbox` still work but are deprecated.
diff --git a/.changeset/eve-tool-listed-tools.md b/.changeset/eve-tool-listed-tools.md
deleted file mode 100644
index a9420a6e0..000000000
--- a/.changeset/eve-tool-listed-tools.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-`eve__tool` now runs a tool from the agent's tool list, other than eve's own catalog and task tools and tools a provider or client runs, instead of returning an error, so a model that routes a listed tool through it no longer wastes a step.
diff --git a/.changeset/fresh-reminder-updates.md b/.changeset/fresh-reminder-updates.md
deleted file mode 100644
index ae5785934..000000000
--- a/.changeset/fresh-reminder-updates.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": minor
----
-
-Add dynamic schedule updates for timing and complete payload replacement, with prepared-payload approval for model calls. Payload replacement makes the updating caller the new creator; custom schedule providers must implement `update`, and `preparePayload` now receives a `create` or `update` operation.
diff --git a/.changeset/gateway-native-web-search.md b/.changeset/gateway-native-web-search.md
deleted file mode 100644
index 979c7b64d..000000000
--- a/.changeset/gateway-native-web-search.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-`webSearch({ provider: "native" })` uses the model vendor's own hosted search for AI Gateway models: OpenAI web search for OpenAI models, Anthropic web search for Anthropic models, and Google Search grounding for Gemini 3 and later, instead of Exa. Other Gateway models don't get `web_search` with this setting unless you set `fallback`, for example `webSearch({ provider: "native", fallback: "exa" })`. Gemini models before Gemini 3, including direct ones, no longer get Google Search, which made the model drop every other tool.
diff --git a/.changeset/local-vercel-dynamic-schedules.md b/.changeset/local-vercel-dynamic-schedules.md
deleted file mode 100644
index 849574869..000000000
--- a/.changeset/local-vercel-dynamic-schedules.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Dynamic schedules now use Vercel's local scheduler and queue delivery under `vc dev`, so cron and one-time occurrences fire automatically. The local consumer loads only for Vercel-backed dynamic collections; standalone `eve dev` keeps its in-memory scheduling backend.
diff --git a/.changeset/quiet-streams-rest.md b/.changeset/quiet-streams-rest.md
deleted file mode 100644
index 38be81340..000000000
--- a/.changeset/quiet-streams-rest.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Remove the stream-writer WebSocket default added in 0.73.0, which never took effect. Behavior is unchanged.
diff --git a/.changeset/remote-agent-uncertain-outcomes.md b/.changeset/remote-agent-uncertain-outcomes.md
deleted file mode 100644
index dc1f91f02..000000000
--- a/.changeset/remote-agent-uncertain-outcomes.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Remote-agent create requests now report that work may have completed when a successful response has an incompatible protocol or unreadable body. These failures stop automatic workflow retries, and protocol mismatches include the remote session ID for checking the outcome.
diff --git a/.changeset/report-datadog-runtime-trace-links.md b/.changeset/report-datadog-runtime-trace-links.md
deleted file mode 100644
index 329bc2c3c..000000000
--- a/.changeset/report-datadog-runtime-trace-links.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": patch
----
-
-Datadog Experiment reports now link each eval to its sampled runtime traces using Datadog-indexed IDs. Linked traces include classified structural spans and, when capture is enabled, turn-level task input and output; zero-duration Experiment spans are normalized to a positive duration. Canonical runtime spans remain unchanged.
diff --git a/.changeset/resumable-slack-setup.md b/.changeset/resumable-slack-setup.md
deleted file mode 100644
index 7a398e0d4..000000000
--- a/.changeset/resumable-slack-setup.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"eve": minor
----
-
-`eve add channel/slack` now resumes interrupted setup, reopens workspace installation for existing connectors, fixes stale routes without detaching, and avoids sharing a Slack app with another project or creating one with a taken name. The `eve/setup` Slack provisioning API now takes a connector selection from `inspectSlackbotConnectors` rather than inspecting a second time; a failed Vercel create reports its original error instead of a misleading cleanup failure.
diff --git a/packages/eve/CHANGELOG.md b/packages/eve/CHANGELOG.md
index 41a71d18b..59e97a454 100644
--- a/packages/eve/CHANGELOG.md
+++ b/packages/eve/CHANGELOG.md
@@ -1,5 +1,47 @@
# eve
+## 0.76.0
+
+### Minor Changes
+
+- 8c55ea7: Skills now load through `eve__skill({ name })`, which every agent with a skill has in place of `load_skill`, and a skill with `deferred: true` (in `SKILL.md` frontmatter or on `defineSkill`, static or dynamic) leaves the system prompt and is found with `eve__search` instead.
+
+ - The `load_skill` tool and the `eve/tools/load_skill` export are removed. Delete any `agent/tools/load_skill.ts` override or approval policy that names it; an authored `agent/tools/load_skill.ts` is now an ordinary tool.
+ - A skill load's `load-skill` action now carries the skill's `name`, and its `input` is the model's `{ name }` instead of `{ skill }`. Its result is a `load-skill-result` with the same `name` instead of a `tool-result` named `load_skill`. Its client message part has the `toolName` `eve__skill` instead of `eve:load-skill`, with the skill's name in `toolMetadata.eve.name`. Sessions recorded by earlier versions replay with `name` filled in from `input.skill`.
+ - Eval facts report skill loads in `skillLoads`, which `t.loadedSkill` reads. They no longer count toward `toolCallCount`, `usedNoTools`, or `maxToolCalls`.
+ - Skill names must use only ASCII letters, digits, underscores, and dashes, start with a letter or digit, and have at most 64 characters. The compiler rejects a static skill with another name, and eve skips a dynamic skill resolver that returns one.
+- 8c55ea7: An agent with deferred entries or connections now has `eve__search` to find tools marked `deferred: true`, agents marked `tool: "deferred"`, and every connection tool, and `eve__tool` to call them, without growing the model's tool list. An agent with skills has `eve__skill` to load them, and `eve__search` also finds deferred skills. An agent with none of these gets no catalog tools, so its tool list is unchanged apart from `load_skill` becoming `eve__skill`. They replace `connection_search` and `connection_execute`, and stream events, approvals, hooks, and traces now name each connection tool call `<connection>__<tool>`. `eve__search` never asks the user to sign in: it lists a connection that needs sign-in under the connection's own name, and `eve__tool` on that name, such as `eve__tool({ name: "linear" })`, asks the user to sign in. `eve__search` takes a required `query`; a query such as `linear__` searches only that connection's tools.
+
+ Breaking changes:
+
+ - The tools eve adds itself now live in the `eve` namespace: `task_wait` is `eve__task_wait`, `task_cancel` is `eve__task_cancel`, and `final_output`, the tool a session with an output schema calls to deliver its structured result, is `eve__reply`. The catalog tools are `eve__search`, `eve__tool`, and `eve__skill`. Update evals, approval policies, hooks, and channel code that match `task_wait`, `task_cancel`, or `final_output` by name. A turn held on `task_wait` when you upgrade stays held until the next message or a cancel.
+ - eve reserves the `eve` namespace. A tool, subagent, skill, connection, or extension mount named `eve` or starting with `eve__` now fails to build, or fails when the agent loads or a dynamic entry resolves; rename it. `search`, `execute`, `task_wait`, `task_cancel`, and `final_output` are ordinary names again.
+ - A connection owns its name and every name starting with `<name>__`. A tool, subagent, or connection under another connection's prefix is rejected at build time, and a dynamic one when it resolves.
+ - Dynamic tool map keys must be legal tool names: ASCII letters, digits, `_`, and `-`, starting with a letter, up to 64 characters.
+ - Connection approvals are keyed by `<connection>__<tool>` instead of a `[connection, tool]` pair, so saved "always approve" decisions for connection tools reset.
+ - A `connection_execute` call still waiting for approval when you upgrade fails when someone answers it, with "The tool "connection_execute" is no longer available, so the call didn't run."
+ - Eval tool-name helpers (`calledTool`, `notCalledTool`, `toolOrder`, and `requireToolCall`) now throw, saying what to assert instead, for `eve__tool` and `eve__skill`, whose calls are reported under the entry they reach and as skill loads, and for a retired eve tool name (`load_skill`, `task_wait`, `task_cancel`, `final_output`, `connection_search`, `connection_execute`) unless the root agent declares a tool by that name or has a dynamic tool resolver. Before, `notCalledTool` on one of these names always passed. `usedNoTools` and `maxToolCalls` count `eve__search` calls; skill loads no longer do.
+ - Removed: the `parentCallId` field on `tool-call` actions in `actions.requested` events, and the `agent.action.parent_call_id` span attribute. The subagent `parentCallId` on `session.started` invocation metadata is unchanged.
+- 2cc43ca: GitHub work moves out of `eve/extensions/code` into a new built-in extension, `eve/extensions/git`. The code extension used to tell every agent that "GitHub credentials are not available to ordinary `bash`" and to route GitHub work through its `gh` tool, which only works with Connect-brokered `github` config. Agents whose shell already has `gh` credentials were steered to a tool that could not authenticate.
+
+ `git({})` adds the GitHub instructions and a `git__pr` skill that commits, pushes, and opens a draft with the shell's `gh pr create --draft`. `git({ github })` adds the Connect-brokered `git__gh` tool and switches `git__pr` to the signed-commit workflow. The tool and sandbox helpers are exported from `eve/extensions/git/tools` and `eve/extensions/git/sandbox`.
+
+ Deprecated: `code({ github })`. While it is set, the code extension still contributes `code__gh`, its GitHub instructions, and the signed-commit `code__pr` skill. Without it, `code({})` no longer contributes `code__gh`, `code__pr`, or any GitHub instructions; mount `eve/extensions/git` for the pull request skill. `gh` from `eve/extensions/code/tools` and the GitHub shell helpers from `eve/extensions/code/sandbox` still work but are deprecated.
+- 14f2af0: Add dynamic schedule updates for timing and complete payload replacement, with prepared-payload approval for model calls. Payload replacement makes the updating caller the new creator; custom schedule providers must implement `update`, and `preparePayload` now receives a `create` or `update` operation.
+- 0ef5c4c: `eve add channel/slack` now resumes interrupted setup, reopens workspace installation for existing connectors, fixes stale routes without detaching, and avoids sharing a Slack app with another project or creating one with a taken name. The `eve/setup` Slack provisioning API now takes a connector selection from `inspectSlackbotConnectors` rather than inspecting a second time; a failed Vercel create reports its original error instead of a misleading cleanup failure.
+
+### Patch Changes
+
+- 32aaf68: Accept create-session responses from remote agents on eve 0.66–0.68 (protocol 1). A newer parent no longer fails a call that the older remote already accepted and is running.
+- 8c55ea7: Catalog calls now read as what happened: `eve__search` shows `Search tools for “linear issues”` and then how much it found, a skill load shows `Load skill <name>` and then `Loaded skill <name>`, and a connection's sign-in entry shows `Sign in to Linear`. Linear activities, Chat SDK typing indicators, and ACP tool calls now show each call's label instead of its raw tool name, and `eve/client` tool parts carry that text as `toolMetadata.eve.label`.
+- 47f1f18: `grep` and `apply_patch` in `eve/extensions/code` now work in sandboxes whose workspace is not `/workspace`, such as `/app`. `apply_patch` no longer requires a git checkout: `root` is optional and defaults to the workspace root, and outside git it still reports whitespace problems the patch introduced. It also accepts unified-diff range headers such as `@@ -118,8 +118,8 @@ def second():`, using the function context to pick between identical blocks.
+- afe7058: `eve__tool` now runs a tool from the agent's tool list, other than eve's own catalog and task tools and tools a provider or client runs, instead of returning an error, so a model that routes a listed tool through it no longer wastes a step.
+- f8ea556: `webSearch({ provider: "native" })` uses the model vendor's own hosted search for AI Gateway models: OpenAI web search for OpenAI models, Anthropic web search for Anthropic models, and Google Search grounding for Gemini 3 and later, instead of Exa. Other Gateway models don't get `web_search` with this setting unless you set `fallback`, for example `webSearch({ provider: "native", fallback: "exa" })`. Gemini models before Gemini 3, including direct ones, no longer get Google Search, which made the model drop every other tool.
+- 73adcdf: Dynamic schedules now use Vercel's local scheduler and queue delivery under `vc dev`, so cron and one-time occurrences fire automatically. The local consumer loads only for Vercel-backed dynamic collections; standalone `eve dev` keeps its in-memory scheduling backend.
+- f15eaa6: Remove the stream-writer WebSocket default added in 0.73.0, which never took effect. Behavior is unchanged.
+- 192732a: Remote-agent create requests now report that work may have completed when a successful response has an incompatible protocol or unreadable body. These failures stop automatic workflow retries, and protocol mismatches include the remote session ID for checking the outcome.
+- c25caf3: Datadog Experiment reports now link each eval to its sampled runtime traces using Datadog-indexed IDs. Linked traces include classified structural spans and, when capture is enabled, turn-level task input and output; zero-duration Experiment spans are normalized to a positive duration. Canonical runtime spans remain unchanged.
+
## 0.75.1
### Patch Changes
diff --git a/packages/eve/package.json b/packages/eve/package.json
index 59a8d3a1c..6ba67227f 100644
--- a/packages/eve/package.json
+++ b/packages/eve/package.json
@@ -1,6 +1,6 @@
{
"name": "eve",
- "version": "0.75.1",
+ "version": "0.76.0",
"private": false,
"description": "Filesystem-first framework for durable backend AI agents that run anywhere.",
"keywords": [