The Open Framework for Building Agents
Version Packages (#4116)
github-actions[bot]61813722eed4
diff --git a/.changeset/approval-sign-in-attempt-id.md b/.changeset/approval-sign-in-attempt-id.mddeleted file mode 100644index f48e7767c..000000000--- a/.changeset/approval-sign-in-attempt-id.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------A sign-in prompt that eve raises while checking who may answer an approval now includes its `attemptId`, so clients match the completion to that prompt instead of leaving it open.diff --git a/.changeset/connection-search-never-prompts.md b/.changeset/connection-search-never-prompts.mddeleted file mode 100644index 889f5750d..000000000--- a/.changeset/connection-search-never-prompts.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------A plain `connection_search` no longer asks the user to sign in: connections they have not authorized appear under `unavailable` with `requiresSignIn: true`, and the model signs in to one connection at a time with `connection_search({ connection, signIn: true })`. A turn waiting on several sign-ins resumes once all of them are done.diff --git a/.changeset/dynamic-remote-credentials-build-error.md b/.changeset/dynamic-remote-credentials-build-error.mddeleted file mode 100644index defe942f1..000000000--- a/.changeset/dynamic-remote-credentials-build-error.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------The build now fails when a dynamic remote agent's `auth` or `headers` uses a value declared inside the event handler. Before, eve moved the credentials to module scope anyway, so they threw at request time or silently read a same-named module value. Dynamic remote agents imported through an alias or `import * as eve` now compile their credentials too.diff --git a/.changeset/eval-derived-models.md b/.changeset/eval-derived-models.mddeleted file mode 100644index 03e9dcf3e..000000000--- a/.changeset/eval-derived-models.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Eval results now list the models their steps started with: `derived.models` on each session holds the distinct model ids in first-use order, and the eval result's `derived.models` merges them in session order. Only the sessions an eval created or attached are covered.diff --git a/.changeset/eve-dev-agent-store.md b/.changeset/eve-dev-agent-store.mddeleted file mode 100644index f4672bf09..000000000--- a/.changeset/eve-dev-agent-store.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------The `eve dev` terminal UI now runs on the shared agent store: the prompt stays open while the agent works, including turns the agent starts on its own, approvals and questions open as soon as they arrive, and slash commands run immediately. `Esc` or `Ctrl+C` cancels the running turn instead of steering with queued messages, and an approval or question names the task that asked. While a sign-in is open, the turn bar names the connection it waits for, and a turn cancelled from another client puts its message back in the prompt.diff --git a/.changeset/held-sign-in-and-approval.md b/.changeset/held-sign-in-and-approval.mddeleted file mode 100644index dad8457ac..000000000--- a/.changeset/held-sign-in-and-approval.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": minor------A connection sign-in or tool approval now holds the turn open, like a question or task: the stream emits `turn.waiting` instead of `turn.completed` and `session.waiting`, and the same turn resumes once the person acts. Every `turn.waiting` now carries `on`: `"input"` when a person must act, `"tasks"` when the turn waits on its own work. A message from that person steers the turn and cancels the pending sign-in or approval, messages from anyone else wait for the turn to end, and cancelling the turn withdraws both, so an approval no longer stays answerable after a cancel. A message sent while a session-limit prompt holds the turn waits in that turn and runs once the budget is granted. Slack's sign-in prompt gains a Cancel button.diff --git a/.changeset/humanize-tool-labels.md b/.changeset/humanize-tool-labels.mddeleted file mode 100644index dbd0becfd..000000000--- a/.changeset/humanize-tool-labels.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Tool, agent, and connection names now read as plain words in activity labels, approval prompts, and the Slack status and task card. An extension or memory namespace before `__` is dropped, and `sync_accounts` or `syncAccounts` shows as `Sync accounts`. A connection call shows as `Linear: List issues`, and its approval asks `Approve Linear: List issues?` instead of naming `connection_execute`. Agent calls read as `Researcher: Find the March incidents`. Labels set with `label.start` are unchanged.diff --git a/.changeset/late-workflow-approval-result.md b/.changeset/late-workflow-approval-result.mddeleted file mode 100644index 0c551387f..000000000--- a/.changeset/late-workflow-approval-result.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Keep a tool's completed result visible when an approval decision arrives after that result. The TUI no longer shows a finished workflow call as interrupted during subsequent turns.diff --git a/.changeset/nested-agent-traces.md b/.changeset/nested-agent-traces.mddeleted file mode 100644index 540583682..000000000--- a/.changeset/nested-agent-traces.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": minor------The first local subagent turn now uses its caller's trace; remote turns remain separate roots with dispatch links, and later child turns start new traces. Queries that followed local `eve.link.type=agent.dispatch` links must use `parentSpanId` or `agent.parent_run.id` and `agent.parent_call.id`; third-party spans receive the conversation ID only when they do not set one.diff --git a/.changeset/nested-extension-mount-config.md b/.changeset/nested-extension-mount-config.mddeleted file mode 100644index b9f266741..000000000--- a/.changeset/nested-extension-mount-config.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Extensions mounted inside a contributed subagent can now read the enclosing extension's configuration. Previously the nested mount saw an unbound handle, so deriving its configuration from the parent extension failed with `Invalid extension config`.diff --git a/.changeset/nuxt-dev-server-parity.md b/.changeset/nuxt-dev-server-parity.mddeleted file mode 100644index 0e50ddf06..000000000--- a/.changeset/nuxt-dev-server-parity.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------`eve/nuxt` now shares the Next.js dev-server startup: it waits up to 180 seconds by default (configurable with the new `devServerTimeoutMs` option), ignores non-local URLs in eve's startup output, and prefixes eve's logs with `[eve:dev]`. Restarting `nuxt dev` no longer leaves eve requests proxied to a stopped dev server.diff --git a/.changeset/one-sign-in-per-connect-grant.md b/.changeset/one-sign-in-per-connect-grant.mddeleted file mode 100644index 3b4de57a7..000000000--- a/.changeset/one-sign-in-per-connect-grant.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Tools and connections that share one Vercel Connect connector now ask the user to sign in once. Before, each tool that called `ctx.getToken(connect(...))` and each connection using the same connector posted its own sign-in prompt for the same grant.diff --git a/.changeset/quiet-live-task-panel.md b/.changeset/quiet-live-task-panel.mddeleted file mode 100644index 4ec912afd..000000000--- a/.changeset/quiet-live-task-panel.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Task starts in the terminal UI now use ordinary tool-call styling. A bounded activity drawer above the prompt shows readable subagent labels, nested work, and the parent's current state and elapsed time. Activity remains visible above questions and approvals when screen space permits.diff --git a/.changeset/remote-agent-own-trace-session.md b/.changeset/remote-agent-own-trace-session.mddeleted file mode 100644index a404dfbe3..000000000--- a/.changeset/remote-agent-own-trace-session.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------On Vercel, a remote agent's spans now carry its own session ID as `vercel.session_id` instead of the calling deployment's root session, and its local subagents carry the same ID. Agent Runs in the receiving project lists the remote agent as its own session, with its turns, subagents, and token usage. `gen_ai.conversation.id` still names the caller's conversation.diff --git a/.changeset/session-history-cursor-value.md b/.changeset/session-history-cursor-value.mddeleted file mode 100644index fe08705f9..000000000--- a/.changeset/session-history-cursor-value.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Session workflow steps that only publish events or update session state, such as a workflow tool's progress report, no longer store the conversation history in their Workflow step input, so their stored size stops growing with the conversation. The session handoff checkpoint changed shape, so an idle session does not move between deployments on either side of this release; its current owner keeps running it.diff --git a/.changeset/session-usage-on-waiting.md b/.changeset/session-usage-on-waiting.mddeleted file mode 100644index 492f86e05..000000000--- a/.changeset/session-usage-on-waiting.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------`session.waiting`, `turn.waiting`, `session.failed`, and `session.completed` now carry `usage`, the session's running token usage and cost including what the agents it delegated to spent. Eval results expose it as `derived.usage`, per session and summed for the eval, so a delegating eval no longer reports only its own model calls.diff --git a/.changeset/severity-based-tui-logs.md b/.changeset/severity-based-tui-logs.mddeleted file mode 100644index 2a67296a1..000000000--- a/.changeset/severity-based-tui-logs.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": minor------The TUI's `--logs` and `/loglevel` modes are now `none`, `error` (default), `warn`, `debug`, and `all`, replacing the `stderr` and `sandbox` filters. Console warnings retain their severity across local server workers, stay hidden by default, and render yellow when enabled; unclassified output is shown only with `all`, in neutral styling. Complete log records now commit immediately instead of holding completed turns in the clipped live region.diff --git a/.changeset/shared-conversation-client.md b/.changeset/shared-conversation-client.mddeleted file mode 100644index 88a56912d..000000000--- a/.changeset/shared-conversation-client.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": minor------Frontend hooks and `EveAgentStore` now share one conversation client: default hooks return `ConversationState` (messages plus root turns, input requests, tasks, and agent sessions) instead of `EveMessageData`, and every snapshot exposes canonical `conversation` alongside a custom reducer's `data`. Answers to open input requests are accepted while a turn runs, `followSubagents: true` follows each agent tool's session into `conversation.agents`, a held turn stays `streaming` with `turns[turnId].waiting` set, and `EveAgentStore` adds a `client` option plus `compact()`, `clear()`, and `retire()`.diff --git a/.changeset/sign-in-resumes-as-requester.md b/.changeset/sign-in-resumes-as-requester.mddeleted file mode 100644index da5c81fd1..000000000--- a/.changeset/sign-in-resumes-as-requester.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------A completed sign-in now resumes the turn as the user who started it. Before, when someone else posted in a shared thread while the sign-in was pending, the resumed turn ran as that last speaker and failed with "the service rejected the token immediately after authorization".diff --git a/.changeset/slack-approval-cleanup.md b/.changeset/slack-approval-cleanup.mddeleted file mode 100644index 0366468d0..000000000--- a/.changeset/slack-approval-cleanup.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Slack now cleans up after a tool approval. Once it resolves, the separate tool-input post is deleted, a direct-message approval's `Waiting on approval` note in the thread shows the outcome, and the card loses its buttons even when the approval ends without a click. The `Checking whether you can respond to this approval…` notice is no longer posted, since Slack cannot remove it afterwards.diff --git a/.changeset/slack-final-reply-delivery.md b/.changeset/slack-final-reply-delivery.mddeleted file mode 100644index 469a50dc5..000000000--- a/.changeset/slack-final-reply-delivery.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Slack no longer drops a final reply without a trace. When Slack refuses eve's default reply as too large or malformed, eve uploads it as a Markdown snippet. When a reply still isn't delivered, including when a custom renderer throws, eve posts a short notice with an error id, without the reply, and tells the model on the next message that the user never saw it. Custom renderers can opt in to the same fallbacks by posting through `postCompletedSlackReply` from `eve/channels/slack`, which tries their blocks, then native Markdown, then a snippet, using only the content they pass.diff --git a/.changeset/slack-installation-team-principal.md b/.changeset/slack-installation-team-principal.mddeleted file mode 100644index c03cf64a7..000000000--- a/.changeset/slack-installation-team-principal.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Slack now identifies a person by the app installation workspace on both messages and button clicks, as `slack:<installation team>:<user>`. Before, a Slack Connect or Enterprise Grid user could get one principal from their messages and another from approval clicks, so they were asked to sign in to the same connection again. Their principal changes once with this release, so they sign in to user-scoped connections one more time.diff --git a/.changeset/slack-onmessage-skip-edits.md b/.changeset/slack-onmessage-skip-edits.mddeleted file mode 100644index 04c31b4a6..000000000--- a/.changeset/slack-onmessage-skip-edits.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Slack `onMessage` now receives only newly posted messages. Edits, deletions, and other system message events go to `onEvent`, so updating the agent's own HITL card in a DM no longer starts a stray session.diff --git a/.changeset/slack-reviewing-results-status.md b/.changeset/slack-reviewing-results-status.mddeleted file mode 100644index 53547a2c8..000000000--- a/.changeset/slack-reviewing-results-status.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Channels can now handle `step.started`, which fires before each model call in a turn. The default Slack channel uses it to replace a stale thread status when the model starts another step. The status shows `Reviewing results...` after a task finishes and `Thinking...` after a tool call. Before, `Waiting on 3 tasks...` or a finished tool's label lingered until the model streamed its next output.diff --git a/.changeset/slack-sign-in-prompt-copy.md b/.changeset/slack-sign-in-prompt-copy.mddeleted file mode 100644index 658ba63d4..000000000--- a/.changeset/slack-sign-in-prompt-copy.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Slack sign-in prompts now say which service they are for and why. The private message reads `Connect Linear: To continue, I need access to your Linear account` with a `Connect Linear` button, and a device code, when the provider issues one, appears as a short hint below the button instead of leading with `Use code … when prompted`. The thread status names who it is waiting on, as in `Waiting for @alice to connect Linear…`.diff --git a/.changeset/stable-message-part-ids.md b/.changeset/stable-message-part-ids.mddeleted file mode 100644index 274621456..000000000--- a/.changeset/stable-message-part-ids.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------The default message reducer gives assistant text and reasoning parts a stable `id` across streaming, completion, and replay, and keeps late-arriving participant messages ahead of their turn's response. Authorization parts match completions by `attemptId` and mark callback-backed sign-ins with `awaitsCallback`; replayed tool events no longer reopen a settled approval, and rejected tool results render as denied.diff --git a/.changeset/telegram-ask-question-buttons.md b/.changeset/telegram-ask-question-buttons.mddeleted file mode 100644index 944813892..000000000--- a/.changeset/telegram-ask-question-buttons.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Pressing a Telegram inline button for an `ask_question` question now answers it. Since `[email protected]` the press was dropped and the agent kept waiting for an answer.diff --git a/.changeset/web-chat-service-build.md b/.changeset/web-chat-service-build.mddeleted file mode 100644index 63b7386b9..000000000--- a/.changeset/web-chat-service-build.md+++ /dev/null@@ -1,5 +0,0 @@-----"eve": patch------Fix generated Web Chat service builds with root-installed pnpm dependencies, and honor Vercel services configuration during project creation instead of prompting to switch to Next.js or eve. Deployment now shows Vercel build logs in the CLI and TUI and provides a command to retrieve them after a failure.diff --git a/packages/eve-buzz-acp-adapter/CHANGELOG.md b/packages/eve-buzz-acp-adapter/CHANGELOG.mdindex f4e7a2eb7..d524e5d88 100644--- a/packages/eve-buzz-acp-adapter/CHANGELOG.md+++ b/packages/eve-buzz-acp-adapter/CHANGELOG.md@@ -1,5 +1,39 @@# @eve/buzz-acp-adapter+## 0.0.41++### Patch Changes++- Updated dependencies [8aca3d8]+- Updated dependencies [ddc8e12]+- Updated dependencies [ac77188]+- Updated dependencies [1094e52]+- Updated dependencies [8aca3d8]+- Updated dependencies [ddc8e12]+- Updated dependencies [001cc00]+- Updated dependencies [8aca3d8]+- Updated dependencies [9553b51]+- Updated dependencies [4361876]+- Updated dependencies [3f6d9cf]+- Updated dependencies [ddc8e12]+- Updated dependencies [a79fca4]+- Updated dependencies [4403122]+- Updated dependencies [384af57]+- Updated dependencies [ff12e85]+- Updated dependencies [63f86de]+- Updated dependencies [8aca3d8]+- Updated dependencies [ddc8e12]+- Updated dependencies [ddc8e12]+- Updated dependencies [490ac0d]+- Updated dependencies [ddc8e12]+- Updated dependencies [19a2b4f]+- Updated dependencies [001cc00]+- Updated dependencies [ddc8e12]+- Updated dependencies [8aca3d8]+- Updated dependencies [b3fc842]+- Updated dependencies [e1130dd]+## 0.0.40### Patch Changesdiff --git a/packages/eve-buzz-acp-adapter/package.json b/packages/eve-buzz-acp-adapter/package.jsonindex f099f2dbb..bf335ddaf 100644--- a/packages/eve-buzz-acp-adapter/package.json+++ b/packages/eve-buzz-acp-adapter/package.json@@ -1,6 +1,6 @@{"name": "@eve/buzz-acp-adapter",- "version": "0.0.40",+ "version": "0.0.41","description": "Buzz ACP compatibility adapter for eve agents.","keywords": ["acp",diff --git a/packages/eve/CHANGELOG.md b/packages/eve/CHANGELOG.mdindex fa8ffd1c6..86185c8c3 100644--- a/packages/eve/CHANGELOG.md+++ b/packages/eve/CHANGELOG.md@@ -1,5 +1,41 @@# eve+## 0.70.0++### Minor Changes++- ddc8e12: A connection sign-in or tool approval now holds the turn open, like a question or task: the stream emits `turn.waiting` instead of `turn.completed` and `session.waiting`, and the same turn resumes once the person acts. Every `turn.waiting` now carries `on`: `"input"` when a person must act, `"tasks"` when the turn waits on its own work. A message from that person steers the turn and cancels the pending sign-in or approval, messages from anyone else wait for the turn to end, and cancelling the turn withdraws both, so an approval no longer stays answerable after a cancel. A message sent while a session-limit prompt holds the turn waits in that turn and runs once the budget is granted. Slack's sign-in prompt gains a Cancel button.+- 9553b51: The first local subagent turn now uses its caller's trace; remote turns remain separate roots with dispatch links, and later child turns start new traces. Queries that followed local `eve.link.type=agent.dispatch` links must use `parentSpanId` or `agent.parent_run.id` and `agent.parent_call.id`; third-party spans receive the conversation ID only when they do not set one.+- 63f86de: The TUI's `--logs` and `/loglevel` modes are now `none`, `error` (default), `warn`, `debug`, and `all`, replacing the `stderr` and `sandbox` filters. Console warnings retain their severity across local server workers, stay hidden by default, and render yellow when enabled; unclassified output is shown only with `all`, in neutral styling. Complete log records now commit immediately instead of holding completed turns in the clipped live region.+- 8aca3d8: Frontend hooks and `EveAgentStore` now share one conversation client: default hooks return `ConversationState` (messages plus root turns, input requests, tasks, and agent sessions) instead of `EveMessageData`, and every snapshot exposes canonical `conversation` alongside a custom reducer's `data`. Answers to open input requests are accepted while a turn runs, `followSubagents: true` follows each agent tool's session into `conversation.agents`, a held turn stays `streaming` with `turns[turnId].waiting` set, and `EveAgentStore` adds a `client` option plus `compact()`, `clear()`, and `retire()`.++### Patch Changes++- 8aca3d8: A sign-in prompt that eve raises while checking who may answer an approval now includes its `attemptId`, so clients match the completion to that prompt instead of leaving it open.+- ddc8e12: A plain `connection_search` no longer asks the user to sign in: connections they have not authorized appear under `unavailable` with `requiresSignIn: true`, and the model signs in to one connection at a time with `connection_search({ connection, signIn: true })`. A turn waiting on several sign-ins resumes once all of them are done.+- ac77188: The build now fails when a dynamic remote agent's `auth` or `headers` uses a value declared inside the event handler. Before, eve moved the credentials to module scope anyway, so they threw at request time or silently read a same-named module value. Dynamic remote agents imported through an alias or `import * as eve` now compile their credentials too.+- 1094e52: Eval results now list the models their steps started with: `derived.models` on each session holds the distinct model ids in first-use order, and the eval result's `derived.models` merges them in session order. Only the sessions an eval created or attached are covered.+- 8aca3d8: The `eve dev` terminal UI now runs on the shared agent store: the prompt stays open while the agent works, including turns the agent starts on its own, approvals and questions open as soon as they arrive, and slash commands run immediately. `Esc` or `Ctrl+C` cancels the running turn instead of steering with queued messages, and an approval or question names the task that asked. While a sign-in is open, the turn bar names the connection it waits for, and a turn cancelled from another client puts its message back in the prompt.+- 001cc00: Tool, agent, and connection names now read as plain words in activity labels, approval prompts, and the Slack status and task card. An extension or memory namespace before `__` is dropped, and `sync_accounts` or `syncAccounts` shows as `Sync accounts`. A connection call shows as `Linear: List issues`, and its approval asks `Approve Linear: List issues?` instead of naming `connection_execute`. Agent calls read as `Researcher: Find the March incidents`. Labels set with `label.start` are unchanged.+- 8aca3d8: Keep a tool's completed result visible when an approval decision arrives after that result. The TUI no longer shows a finished workflow call as interrupted during subsequent turns.+- 4361876: Extensions mounted inside a contributed subagent can now read the enclosing extension's configuration. Previously the nested mount saw an unbound handle, so deriving its configuration from the parent extension failed with `Invalid extension config`.+- 3f6d9cf: `eve/nuxt` now shares the Next.js dev-server startup: it waits up to 180 seconds by default (configurable with the new `devServerTimeoutMs` option), ignores non-local URLs in eve's startup output, and prefixes eve's logs with `[eve:dev]`. Restarting `nuxt dev` no longer leaves eve requests proxied to a stopped dev server.+- ddc8e12: Tools and connections that share one Vercel Connect connector now ask the user to sign in once. Before, each tool that called `ctx.getToken(connect(...))` and each connection using the same connector posted its own sign-in prompt for the same grant.+- a79fca4: Task starts in the terminal UI now use ordinary tool-call styling. A bounded activity drawer above the prompt shows readable subagent labels, nested work, and the parent's current state and elapsed time. Activity remains visible above questions and approvals when screen space permits.+- 4403122: On Vercel, a remote agent's spans now carry its own session ID as `vercel.session_id` instead of the calling deployment's root session, and its local subagents carry the same ID. Agent Runs in the receiving project lists the remote agent as its own session, with its turns, subagents, and token usage. `gen_ai.conversation.id` still names the caller's conversation.+- 384af57: Session workflow steps that only publish events or update session state, such as a workflow tool's progress report, no longer store the conversation history in their Workflow step input, so their stored size stops growing with the conversation. The session handoff checkpoint changed shape, so an idle session does not move between deployments on either side of this release; its current owner keeps running it.+- ff12e85: `session.waiting`, `turn.waiting`, `session.failed`, and `session.completed` now carry `usage`, the session's running token usage and cost including what the agents it delegated to spent. Eval results expose it as `derived.usage`, per session and summed for the eval, so a delegating eval no longer reports only its own model calls.+- ddc8e12: A completed sign-in now resumes the turn as the user who started it. Before, when someone else posted in a shared thread while the sign-in was pending, the resumed turn ran as that last speaker and failed with "the service rejected the token immediately after authorization".+- ddc8e12: Slack now cleans up after a tool approval. Once it resolves, the separate tool-input post is deleted, a direct-message approval's `Waiting on approval` note in the thread shows the outcome, and the card loses its buttons even when the approval ends without a click. The `Checking whether you can respond to this approval…` notice is no longer posted, since Slack cannot remove it afterwards.+- 490ac0d: Slack no longer drops a final reply without a trace. When Slack refuses eve's default reply as too large or malformed, eve uploads it as a Markdown snippet. When a reply still isn't delivered, including when a custom renderer throws, eve posts a short notice with an error id, without the reply, and tells the model on the next message that the user never saw it. Custom renderers can opt in to the same fallbacks by posting through `postCompletedSlackReply` from `eve/channels/slack`, which tries their blocks, then native Markdown, then a snippet, using only the content they pass.+- ddc8e12: Slack now identifies a person by the app installation workspace on both messages and button clicks, as `slack:<installation team>:<user>`. Before, a Slack Connect or Enterprise Grid user could get one principal from their messages and another from approval clicks, so they were asked to sign in to the same connection again. Their principal changes once with this release, so they sign in to user-scoped connections one more time.+- 19a2b4f: Slack `onMessage` now receives only newly posted messages. Edits, deletions, and other system message events go to `onEvent`, so updating the agent's own HITL card in a DM no longer starts a stray session.+- 001cc00: Channels can now handle `step.started`, which fires before each model call in a turn. The default Slack channel uses it to replace a stale thread status when the model starts another step. The status shows `Reviewing results...` after a task finishes and `Thinking...` after a tool call. Before, `Waiting on 3 tasks...` or a finished tool's label lingered until the model streamed its next output.+- ddc8e12: Slack sign-in prompts now say which service they are for and why. The private message reads `Connect Linear: To continue, I need access to your Linear account` with a `Connect Linear` button, and a device code, when the provider issues one, appears as a short hint below the button instead of leading with `Use code … when prompted`. The thread status names who it is waiting on, as in `Waiting for @alice to connect Linear…`.+- 8aca3d8: The default message reducer gives assistant text and reasoning parts a stable `id` across streaming, completion, and replay, and keeps late-arriving participant messages ahead of their turn's response. Authorization parts match completions by `attemptId` and mark callback-backed sign-ins with `awaitsCallback`; replayed tool events no longer reopen a settled approval, and rejected tool results render as denied.+- b3fc842: Pressing a Telegram inline button for an `ask_question` question now answers it. Since `[email protected]` the press was dropped and the agent kept waiting for an answer.+- e1130dd: Fix generated Web Chat service builds with root-installed pnpm dependencies, and honor Vercel services configuration during project creation instead of prompting to switch to Next.js or eve. Deployment now shows Vercel build logs in the CLI and TUI and provides a command to retrieve them after a failure.+## 0.69.0### Minor Changesdiff --git a/packages/eve/package.json b/packages/eve/package.jsonindex d1d3d9fd3..6343b3a29 100644--- a/packages/eve/package.json+++ b/packages/eve/package.json@@ -1,6 +1,6 @@{"name": "eve",- "version": "0.69.0",+ "version": "0.70.0","private": false,"description": "Filesystem-first framework for durable backend AI agents that run anywhere.","keywords": [